diff --git a/docs/reference-matrix.md b/docs/reference-matrix.md index 4be14b07c..035b85d72 100644 --- a/docs/reference-matrix.md +++ b/docs/reference-matrix.md @@ -444,6 +444,7 @@ the candidate mechanisms. | --- | --- | --- | | [Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/60#issuecomment-6310920198), 2026-10-21; eight Git source inventories in the [owner metadata](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json) | Task/quality/workload separation across text, agentic coding, work agents, TTS, full-duplex interaction and image/video; selected pinned AIPerf/realtime/FDB/video sources rechecked and the current InferRSI metric contract inspected | Extend [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) with [task selection](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/task-benchmark-selection.md) and [command templates](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/benchmark-commands.md). Candidate guidance; source review and bounded smoke do not qualify all tasks or establish a performance gain. Replay scores, reference parity and task quality retain separate meanings. | | [NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Speech.cpp/tree/20999cc921d2b14aa58708f61756a8b2e787ba20), inspected 2026-11-01 | Selected cache-aware encoder/config, runner, SDK bounds, endpoint policy, geometry test/CMake and ASR benchmark; complete 14-file readset and Apache-2.0 / parakeet MIT attribution retained in the reference | Extend [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) with [cache-aware ASR stream boundaries](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/cache-aware-asr-stream-boundaries.md): first/steady mel geometry and decoded clock, stream-slot reset/reuse, EOU/EOF/reset and model-test SKIP boundaries. Source-derived candidate / empirical not_run; benchmark figures remain author-reported with precision, FE and trial limits. No model/device/quality/long-audio/load/service qualification. | +| [yuekaizhang/faster-cosyvoice @ f1049c59](https://github.com/yuekaizhang/faster-cosyvoice/tree/f1049c59196c2c1a890079abc56056b43f27cd1d), inspected 2026-11-03; overall source rights UNKNOWN, selected file headers retain Apache-2.0 and unresolved inherited attribution | Bounded PCM client/server-credit, chunk planner, session/worker, Token2Wav and timing/quality-report inspection; [exact readset and per-file rights](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json) | Extend [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) with [dependency-aware TTS playout](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md): route-origin credit versus client zero-buffer playback, same-session Mel dependencies, cumulative vocoding and partial-cost/token-derived denominators. Original analysis with immutable links only; candidate / empirical not_run / efficacy not_evaluated. Author reports remain separate; no copied implementation/media, new runtime or hardware/quality/service qualification. | ## SGLang versioned entry selection diff --git a/docs/searchspace-matrix.md b/docs/searchspace-matrix.md index aad404af3..f7600e7ce 100644 --- a/docs/searchspace-matrix.md +++ b/docs/searchspace-matrix.md @@ -614,3 +614,16 @@ NOASSERTION and InferRSI's repository license. | Accelerator / RAM / Host | Diagnose / configure / verify: tensor/alias/gradient state, training and data ownership, compiler guards and export contracts, allocator accounting, stream dependencies and graph input/output lifetimes | [pytorch operating graph](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md), [memory/graph route](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/sub-skills/memory-streams-and-graphs/SKILL.md), [compiler/export route](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/sub-skills/compiler-and-export/SKILL.md) | Source version `2.16.0a0` and observed CPU wheel `2.15.0+cpu` are distinct. CPU observations do not qualify pinned-source execution, CUDA/ROCm/MPS/XPU, native custom operators, memory fit or model quality. | | SSD / Storage / RAM | Diagnose / verify: serialization trust and state identity, checkpoint ownership, distributed restore and capture/staging/upload completion boundaries | `pytorch`: [distributed/checkpoint route](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/sub-skills/distributed-and-checkpoint/SKILL.md); existing [DCP async-save owner](../src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md) retains its separate source pin | No source-build checkpoint run, backend durability, distributed recovery or measured storage benefit is established. A state-dict round trip in a separate installed wheel does not qualify those properties. | | Communication / Network / Accelerator | Diagnose / verify: process/rank/device mapping, backend and collective schedule, DDP/FSDP2/DTensor state and completion | `pytorch`: [distributed/checkpoint route](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/sub-skills/distributed-and-checkpoint/SKILL.md), [source and runtime boundary](../src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/references/repo-provenance.md) | Selected source and CPU controls do not establish NCCL or other accelerator transport, multi-device/multi-node correctness, overlap or throughput. Required backend checks remain `BLOCKED_REQUIRED_BACKEND`; no new measured/green resource cell, OS control or compatible latest PyTorch/TorchNPU stack is asserted. | + +## Faster CosyVoice evaluation source context + +The existing [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) +uses [dependency-aware TTS playout](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md) +and its [source record](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json) +as methodology/source context for server PCM credit, client playback +observations, chunk dependencies and partial cost denominators. This adds no +numbered resource-layer mapping, lifecycle-stage mapping, supplementary +hardware coverage or hardware prerequisite. The owner's existing N/A reason +remains unchanged; source use of GPU, TensorRT, Flow or HiFT does not alter +that boundary. Source-derived candidate / empirical not_run / efficacy +not_evaluated; author reports are not local quality or service results. diff --git a/docs/skill-coverage.md b/docs/skill-coverage.md index 50c3f1b6c..d4afc4acd 100644 --- a/docs/skill-coverage.md +++ b/docs/skill-coverage.md @@ -4,7 +4,7 @@ Generated from the registry, the skill sidecars and the two maintained matrices. **Do not edit by hand**; regenerate after any registry, skill, matrix or frozen-plan change. -- Input digest: `sha256:7640b171256091efd1514a33d5e434eef3feaed238fc92fe3eeba02fee94e9ff` +- Input digest: `sha256:1fe4e1f4ef789646545898c85bbc1584ed4b74d88928c9424910e95559555abe` - Regenerate: `python tools/build_skill_coverage.py` - Verify without writing: `python tools/build_skill_coverage.py --check` @@ -131,7 +131,7 @@ optimization is fully covered or that any procedure has measured benefit. | [choose-parallel-training-plan](../src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md) | common | Compare stage, device-mesh and operator-sharding candidates for static distributed training while accounting for ... | Comparing stage, device-mesh and operator-sharding candidates for static distributed ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify
4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Alpa — [2201.12023v3](https://arxiv.org/abs/2201.12023v3)) | candidate · not_run · 1 readset(s) | no-eval | | [dense-performance-evidence](../src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md) | common | Taxonomy of performance evidence an optimization agent needs, ordered by collection cost and diagnostic power. Maps ... | Deciding which performance evidence to collect next and which claim each evidence level ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Observe / Profile / Verify
2 RAM/Host · Verify
4 Network · Verify | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 0 readset(s) | — | | [evaluate-elastic-serving-placement](../src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md) | common | Compare migrating an LLM request between model replicas with changing its sequence-parallel execution group, including ... | Comparing migration of a running LLM request between compatible model replicas with ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify
2 RAM/Host · Diagnose / Configure / Optimize / Verify
4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Llumnix — [2406.03243v1](https://arxiv.org/abs/2406.03243v1)) | candidate · not_run · 1 readset(s) | no-eval | -| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point
5 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)
Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...) | candidate · not_run · 7 readset(s) | — | +| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point
5 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)
Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...)
Task-specific benchmark selection (issue #60) ([yuekaizhang/faster-cosyvoice @ f1049c59](https://github.com/yuekaizha ...) | candidate · not_run · 9 readset(s) | — | | [inference-optimization-casebook](../src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md) | common | How to structure and use a casebook of past optimization decisions as a decision-support tool. Extracts the casebook ... | Structuring and querying a casebook of past optimization decisions as decision support ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd) | candidate · not_run · 0 readset(s) | no-eval | | [kernel-writing-guide](../src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md) | common | Decision guide for writing custom inference kernels: when to write one, which framework to choose (Triton, CuTe DSL ... | Deciding whether to write a custom inference kernel, routing a kernel pattern to Triton ... | failure_modes, input_contract, produced_artifact, refusal_point
6 advice | 1 Accelerator · Optimize / Diagnose / Configure / Verify | 1 · Systems sources (Dao-AILab/causal-conv1d @ `cd81f0413cad2fc1e6f17e785ac39f59aae690cd` ...)
1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)
1 · Systems sources (huggingface/transformers @ `0dad7b822255a0ae261ec45ae937371e859ffd1a` ...)
1 · Systems sources (mindspore-ai/akg @ `5aa15f3fe4d856eb60cd3b27447e04f5f1fb4dff` ...)
1 · Systems sources (sgl-project/sglang @ `16176278d0180f1a1a578e53e6eef432577876c2` ...)
1 · Systems sources (vllm-project/vllm @ `537a79f0fc5ba564d2bef43d54915b2f80f9f77d` (root ...) | candidate · not_run · 7 readset(s) | no-eval | | [optimization-search-policy](../src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md) | common | Policy for how an optimization agent should select, order, and stop optimization experiments. Covers candidate ... | Selecting, ordering and stopping optimization experiments: candidate generation ... | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Optimize | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)
2 · Methodology and corpus references (RRSI — arXiv 2609.24972v3)
2 · Methodology and corpus references (arXiv 2608.01867 (CRISP))
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 9 readset(s) | no-eval | diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md index 86ee95d7e..ecef2a747 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md @@ -15,7 +15,7 @@ These are knowledge abstracts (`--kind knowledge`), with namespaced package IDs distinct from explicitly selected `checkout_ref` skills. Ascend/CUDA procedures use their corresponding backend; shared methods use `common`. -Source snapshot: [7aa3344bf84c42467f43b3a927e1c7d13642bd55](https://github.com/InferMatrixLab/InferRSI/tree/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library). +Source snapshot: [8daa93343cb7a33069b6c6b53a82eb4ec14941a0](https://github.com/InferMatrixLab/InferRSI/tree/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library). ```bash inferrsi knowledge search 'profiling' --repo-type inferrsi --limit 50 @@ -29,7 +29,7 @@ contain the current input paths and bytes (Git checkout filters are respected). ```bash python tools/build_skill_index.py --source-revision -python tools/build_skill_index.py --source-revision 7aa3344bf84c42467f43b3a927e1c7d13642bd55 --check +python tools/build_skill_index.py --source-revision 8daa93343cb7a33069b6c6b53a82eb4ec14941a0 --check ``` `--check` detects missing, stale and unexpected generated records without writing. diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json index d628bdadd..4e36ca850 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json index f4b372d19..380bd7b89 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json index 4b940539c..cfa0e4ef8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json index 5c1c8590b..59e184dcf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json index 971e9813a..be957937c 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json index e8d595cbc..13ed3808a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json index 64816a247..b5cf3ece9 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json index 7521c9f69..3c0cc3984 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json index 2a4a0ace2..ba4f670d1 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json index a2d677d4d..56a6ca5a7 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json index ea618b662..101542b62 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json index ca740b5b7..7cf14dc83 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json index 7c1cde5ed..56a5728b8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json @@ -20,8 +20,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md", "src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json index d6676b490..085fec843 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json index d6ea1871c..dfbfc606f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json index 12aeca1fd..43f6852bd 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md", "src/inferrsi/data/skill_library/methods/assess-serving-preemption/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json index 7c6e81473..4b9bd2306 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md", "src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json index a3b85ccdc..e8dcb5c7e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json @@ -20,8 +20,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md", "src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json index 50b90d31b..0517c83f3 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/LICENSE", "src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json index c01e0e11f..26f77f186 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json @@ -30,8 +30,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/LICENSE", "src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json index 3adab00f6..745cbb758 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md", "src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json index d5ab3d293..ecebf3559 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/LICENSE", "src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json index 8b883145a..b72f43de6 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/LICENSE", "src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json index 2dab44411..314327edd 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/LICENSE", "src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json index a4074b797..e8140380b 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md", "src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json index 3c226dfe4..40f2a2733 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md", "src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json index bb08f2ed5..a4d76fab8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md", "src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json index 3e86452fe..903af50e1 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md", "src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json index a88384b33..544ec548b 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json index 3572a1f8c..d3c5688ff 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md", "src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json index d5ce0bdbf..93c1a2fcb 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md", "src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json index ded00b5e0..463d792bf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json index a7f2bfa5d..689d93d66 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json index acdc57b97..7c7d51604 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/comfy-ui/LICENSE", "src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json index 0f5b0fb34..60f1d5282 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json index 064e2ca25..01f9b2df6 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md", "src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json index b20edd811..c1e42c029 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md", "src/inferrsi/data/skill_library/methods/dense-performance-evidence/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json index 70fd8e8a5..7da696542 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md", "src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json index 3a883cf9a..c68a22cc4 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md", "src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json index e90c2488d..f63413f29 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json index c456f30e9..b908fbc8f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/dwarfstar/LICENSE", "src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json index 3482d1338..96e88deed 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md", "src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json index 7d68adf8b..8dc21be7c 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md", "src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json index bb39eac1d..aa0e47729 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json @@ -30,8 +30,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/host-memory-management/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json index 9f20ba9d7..abc38cb1d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json index 3dee4b666..e3596a30d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/husky/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/husky/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/husky/SKILL.md", "src/inferrsi/data/skill_library/repositories/husky/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json index 3b2327374..1cfbed91b 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json @@ -35,8 +35,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json", @@ -44,12 +44,14 @@ "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/benchmark-commands.md", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/cache-aware-asr-stream-boundaries.md", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/task-benchmark-selection.md", "src/inferrsi/data/skill_library/skill-index.json" ], - "content_sha256": "7fd7f557f5c99ca4ec4c46f2d97e67ecf280f5f0fdf071871a14cc08a7cb1c84" + "content_sha256": "8f319f31e138e4ef41119dbc0de63296c0cc4fad4acc3a9d4d503d33fd3fa5f9" } ], "index_type": "packaged-skill", @@ -58,12 +60,14 @@ }, "checkout_ref": "checkout:inference-benchmark-design", "source_files": { - "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md": "7fd7f557f5c99ca4ec4c46f2d97e67ecf280f5f0fdf071871a14cc08a7cb1c84", - "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json": "a646de55162cb8160f3f0947cab4b6ecac81927c3225019044b3f909087ba048", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md": "8f319f31e138e4ef41119dbc0de63296c0cc4fad4acc3a9d4d503d33fd3fa5f9", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json": "16a63c20c973e5d3ed2b3f7ce7a1f69a7f4e144f5e8ca3ea7deaadba74a05632", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json": "bc343ece2bf40c4e8aa4bd8d84f32465d00633255557feda5fe7799ce24e8688", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md": "cb3a7a5d94d056f868af07f92a16a6fef31eafd3199ed07ae79e93798e320b1d", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/benchmark-commands.md": "0898424e0bff3a6246e1eeeda6abd6c5bd974c047fe32f3bbd5ab9d31ce17cd3", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/cache-aware-asr-stream-boundaries.md": "4e0ea9c1bf6b096a49a91ad5266e90b8a456f4f5aca15eba8ac270a53c2309b5", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md": "e94866e718adc3bd7e272a4856e9a90b6f27cbc0ff3a44101e68e6995ed79e2c", + "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json": "9efe8918208adddfb9a31d2abed080923a5ae0dfb6332438179af0de66f54e13", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md": "d25df795fd301e8a1bb436e5f8122d0bac2441c43104e59a3b310fd5a64f2f3e", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json": "60f2784384ea1a3b08a2ecafb60207d8e3707247dc7bc177b95b463d81f1cc16", "src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/task-benchmark-selection.md": "0d4bb080a754e26846e81680023db0dff5e6a4c96be4327c411c3b72ac4ef8e2", @@ -310,6 +314,49 @@ "Tables 1-7" ], "readset": "references/autotunebench-trial-validity.md" + }, + { + "type": "git", + "url": "https://github.com/yuekaizhang/faster-cosyvoice", + "commit": "f1049c59196c2c1a890079abc56056b43f27cd1d", + "paths": [ + "README.md", + "README_zh.md", + "docs/benchmark.md", + "docs/benchmark_zh.md", + "docs/usage.md", + "docs/usage_zh.md", + "examples/offline_inference.py", + "examples/stream_client.py", + "faster_cosyvoice/config/settings.py", + "faster_cosyvoice/llm/engine.py", + "faster_cosyvoice/server/app.py", + "faster_cosyvoice/server/arguments.py", + "faster_cosyvoice/server/audio_encode.py", + "faster_cosyvoice/server/leading_silence.py", + "faster_cosyvoice/server/openai_speech.py", + "faster_cosyvoice/server/protocol.py", + "faster_cosyvoice/streaming/chunker.py", + "faster_cosyvoice/streaming/session.py", + "faster_cosyvoice/streaming/token2wav_batcher.py", + "faster_cosyvoice/streaming/token2wav_scheduler.py", + "faster_cosyvoice/token2wav/builders.py", + "faster_cosyvoice/token2wav/cosyvoice/flow/DiT/modules.py", + "faster_cosyvoice/token2wav/cosyvoice/flow/flow.py", + "faster_cosyvoice/token2wav/cosyvoice/hifigan/generator.py", + "faster_cosyvoice/token2wav/flashinfer_dit.py", + "faster_cosyvoice/token2wav/flashinfer_flow.py", + "faster_cosyvoice/token2wav/frontend.py", + "faster_cosyvoice/token2wav/matcha_audio.py", + "faster_cosyvoice/token2wav/token2wav.py", + "pyproject.toml", + "tests/test_session.py", + "tests/test_stream_client.py", + "tests/test_token2wav_batcher.py" + ], + "readset": "references/faster-cosyvoice-source.json", + "license": "UNKNOWN overall; selected file-level Apache-2.0 headers and unresolved inherited attribution retained", + "scope": "Selected PCM/playout, routed-credit, chunk-dependency and timing-denominator source audit; original analysis and immutable links only, no code/media copying or native/model/quality/service execution" } ], "empirical_validation": "not_run", @@ -347,7 +394,8 @@ "Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.", "The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.", "JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.", - "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run." + "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.", + "The Faster CosyVoice reference is source-only: server route credit and client simulated playback remain distinct, reported costs/quality retain their boundaries, overall source rights are UNKNOWN, and native/model/device/audio quality/service/performance are not_run with efficacy not_evaluated." ], "provenance_readsets": [ "references/task-benchmark-selection.md", @@ -356,7 +404,9 @@ "references/justgoal-evaluation-contracts.md", "references/justgoal-source.json", "references/autotunebench-trial-validity.md", - "references/autotunebench-source.json" + "references/autotunebench-source.json", + "references/dependency-aware-tts-playout.md", + "references/faster-cosyvoice-source.json" ], "references": [ "../inference-optimization-casebook/cases/admission-drain-occupancy.md", @@ -403,7 +453,8 @@ "Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.", "The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.", "JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.", - "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run." + "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.", + "The Faster CosyVoice reference is source-only: server route credit and client simulated playback remain distinct, reported costs/quality retain their boundaries, overall source rights are UNKNOWN, and native/model/device/audio quality/service/performance are not_run with efficacy not_evaluated." ], "verification": { "locally_verified": false, diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json index 3d6372c43..e6c2ce70d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md", "src/inferrsi/data/skill_library/methods/inference-optimization-casebook/cases/admission-drain-occupancy.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json index 1040189df..89f18117c 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json @@ -39,8 +39,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md", "src/inferrsi/data/skill_library/methods/kernel-writing-guide/cases/causal-conv1d-dispatch-state.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json index 1c1f0ac80..10358cc5f 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md", "src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json index c3b8b61d3..0d5a0b220 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md", "src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json index 8c592e80d..4ee4132bc 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lily/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/lily/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/lily/LICENSE", "src/inferrsi/data/skill_library/repositories/lily/NOTICE.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json index 26722f7f4..42bbbe859 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/lithos-metal/LICENSE", "src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json index cb94c8a24..6a3730e78 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md", "src/inferrsi/data/skill_library/repositories/local-dream/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json index 636fbe213..4d802a9cf 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/mistral-rs/LICENSE", "src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json index b94c5f561..c10e539a4 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/mlc-llm/LICENSE", "src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json index fef01f452..357ef2016 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json @@ -27,8 +27,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/mlx-swift-lm/LICENSE", "src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json index 1adcbdc00..75b6cd497 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json index 8965fb642..4ac4b753e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md", "src/inferrsi/data/skill_library/methods/optimization-search-policy/cases/sarathi-chunk-budget.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json index 8c0cf7b12..becd97595 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/os-process-placement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json index ae1810d82..83fa9996d 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md", "src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json index 5ccb28ffe..9f03701a7 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md", "src/inferrsi/data/skill_library/methods/plan-activation-residency/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json index abec7ae74..e4865d895 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/project-maya/LICENSE", "src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json index 97d160bec..097cf345a 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/LICENSE", "src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json index 27968f7c8..8ce5639e1 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md", "src/inferrsi/data/skill_library/methods/repository-evolution-analysis/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json index 465739baa..90ffee7ba 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/skill-index.json", "src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json index c470e93b8..575e947cc 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json @@ -21,8 +21,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md", "src/inferrsi/data/skill_library/methods/skill-evolution-playbook/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json index a9476f7cf..cce6279b6 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json @@ -25,8 +25,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/splash/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/splash/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/splash/LICENSE", "src/inferrsi/data/skill_library/repositories/splash/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json index fc715e09f..91c84eefe 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json @@ -24,8 +24,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md", "src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json index 045b18bc4..24f9f0060 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md", "src/inferrsi/data/skill_library/methods/training-input-pipeline/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json index a2429cac2..0cb0c49cd 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md", "src/inferrsi/data/skill_library/methods/training-resource-budget/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json index 2fbb6eebc..e19c2247e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md", "src/inferrsi/data/skill_library/methods/video-diffusion-optimization/assets/campaign.template.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json index 179f342ea..aae507db8 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json @@ -26,8 +26,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/vllm-metal/LICENSE", "src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json index 3cc50bdee..d3b6ea251 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md", "src/inferrsi/data/skill_library/methods/weight-loading-optimization/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json index 42b227ef5..d17c1642e 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json @@ -23,8 +23,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md", "src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json index 0fc99822c..5b0406572 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json @@ -29,8 +29,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/LICENSE", "src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json index 19f847d38..a98207092 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json @@ -16,8 +16,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json index 7fac0bc38..eaec8e82c 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json @@ -22,8 +22,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/metadata.json", diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json index 55040913f..8e85cea86 100644 --- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json +++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json @@ -36,8 +36,8 @@ "sources": [ { "type": "git", - "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", - "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55", + "url": "https://github.com/InferMatrixLab/InferRSI/blob/8daa93343cb7a33069b6c6b53a82eb4ec14941a0/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", + "commit": "8daa93343cb7a33069b6c6b53a82eb4ec14941a0", "paths": [ "src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md", "src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/metadata.json", diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md index b40a52d2c..1cb919b06 100644 --- a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md +++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md @@ -24,6 +24,12 @@ before selecting tests or comparing chunk latency. It separates startup/steady g progress, stream-slot reuse, reset, EOU and EOF; its source tests and author benchmark reports are not local model or serving qualification. +For streaming TTS measurements tied to playback deadlines or dependent chunks, +read [dependency-aware TTS playout](references/dependency-aware-tts-playout.md). +It traces server PCM credit, client playback events, independent batching work +and partial pipeline costs at one pinned source; it adds no hardware coverage, +runtime or locally reproduced quality/performance result. + For treatment-enabled tuning comparisons or claimed protocol integrity, read [treatment delivery and trial validity](references/autotunebench-trial-validity.md). Trace feedback to the eligible consumer input and apply the frozen arm-validity diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json index e6ea1ff3b..dfe473cb9 100644 --- a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json +++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json @@ -237,6 +237,49 @@ "Tables 1-7" ], "readset": "references/autotunebench-trial-validity.md" + }, + { + "type": "git", + "url": "https://github.com/yuekaizhang/faster-cosyvoice", + "commit": "f1049c59196c2c1a890079abc56056b43f27cd1d", + "paths": [ + "README.md", + "README_zh.md", + "docs/benchmark.md", + "docs/benchmark_zh.md", + "docs/usage.md", + "docs/usage_zh.md", + "examples/offline_inference.py", + "examples/stream_client.py", + "faster_cosyvoice/config/settings.py", + "faster_cosyvoice/llm/engine.py", + "faster_cosyvoice/server/app.py", + "faster_cosyvoice/server/arguments.py", + "faster_cosyvoice/server/audio_encode.py", + "faster_cosyvoice/server/leading_silence.py", + "faster_cosyvoice/server/openai_speech.py", + "faster_cosyvoice/server/protocol.py", + "faster_cosyvoice/streaming/chunker.py", + "faster_cosyvoice/streaming/session.py", + "faster_cosyvoice/streaming/token2wav_batcher.py", + "faster_cosyvoice/streaming/token2wav_scheduler.py", + "faster_cosyvoice/token2wav/builders.py", + "faster_cosyvoice/token2wav/cosyvoice/flow/DiT/modules.py", + "faster_cosyvoice/token2wav/cosyvoice/flow/flow.py", + "faster_cosyvoice/token2wav/cosyvoice/hifigan/generator.py", + "faster_cosyvoice/token2wav/flashinfer_dit.py", + "faster_cosyvoice/token2wav/flashinfer_flow.py", + "faster_cosyvoice/token2wav/frontend.py", + "faster_cosyvoice/token2wav/matcha_audio.py", + "faster_cosyvoice/token2wav/token2wav.py", + "pyproject.toml", + "tests/test_session.py", + "tests/test_stream_client.py", + "tests/test_token2wav_batcher.py" + ], + "readset": "references/faster-cosyvoice-source.json", + "license": "UNKNOWN overall; selected file-level Apache-2.0 headers and unresolved inherited attribution retained", + "scope": "Selected PCM/playout, routed-credit, chunk-dependency and timing-denominator source audit; original analysis and immutable links only, no code/media copying or native/model/quality/service execution" } ], "empirical_validation": "not_run", @@ -274,7 +317,8 @@ "Benchmark feasibility and package-consumption checks do not promote this candidate or replace task quality, repeated A/B and service qualification.", "The pinned NeMo-Speech.cpp ASR reference covers selected source/test definitions and author-reported benchmark boundaries; native model/device, decoder internals, quality, long-audio/load and service behavior remain not_run.", "JustGoal contributes source-only controlled-evaluation and kernel-acceptance guidance; its repaired/retested timings, released-pass counts and protocol differences are author-reported, not locally reproduced or a complete campaign runner.", - "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run." + "The AutoTuneBench reference is source-only: original operational checkpoint/prompt receipts remain unavailable, source contradictions remain explicit, and no tuning, device/performance or agent-efficacy validation was run.", + "The Faster CosyVoice reference is source-only: server route credit and client simulated playback remain distinct, reported costs/quality retain their boundaries, overall source rights are UNKNOWN, and native/model/device/audio quality/service/performance are not_run with efficacy not_evaluated." ], "provenance_readsets": [ "references/task-benchmark-selection.md", @@ -283,7 +327,9 @@ "references/justgoal-evaluation-contracts.md", "references/justgoal-source.json", "references/autotunebench-trial-validity.md", - "references/autotunebench-source.json" + "references/autotunebench-source.json", + "references/dependency-aware-tts-playout.md", + "references/faster-cosyvoice-source.json" ], "references": [ "../inference-optimization-casebook/cases/admission-drain-occupancy.md", diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md new file mode 100644 index 000000000..af7c7e7f4 --- /dev/null +++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/dependency-aware-tts-playout.md @@ -0,0 +1,196 @@ +# Dependency-aware TTS playout + +Use this reference when designing or auditing a streaming TTS benchmark whose +chunks share model state or are scheduled against estimated playback time. +It derives from [Faster CosyVoice][source] at +`f1049c59196c2c1a890079abc56056b43f27cd1d`, inspected 2026-11-03. The +[source record](faster-cosyvoice-source.json) preserves the exact bounded +readset, file identities and rights. This is source-derived **candidate** +guidance: native/model/device/quality/service execution is **not_run** and +efficacy is **not_evaluated**. + +Keep the [parent method](../SKILL.md) and +[task benchmark selection](task-benchmark-selection.md) for quality gates, +reference parity, comparable workloads, statistics and evidence verdicts. This +reference adds the source-specific playout and cost-accounting prerequisites; +it adds no runtime, hardware prerequisite or measured optimization. + +## 1. Establish the client event and buffer policy + +Before comparing first-audio measurements, record sample rate, channel count, +sample width, encoding, leading-silence policy and the client's playback-buffer +policy. The source client requests mono, 24 kHz, little-endian PCM16. It carries +an odd byte into the next HTTP read and records an audio observation only when +at least one complete sample exists. HTTP reads can split or combine model +chunks; their boundaries are not model chunk identities. [Client][client] + +| Source field | Event or quantity | Interpretation limit | +| --- | --- | --- | +| `ttfb_ms` | First nonempty raw response-body read after request start | An odd byte can arrive before any complete PCM sample; a WAV header is a different payload again | +| `first_playable_ms` | First sample-aligned PCM observation | Receipt of complete samples, not a physical speaker measurement or a guaranteed startup buffer | +| `audible_ttfa_ms` | Detected onset placed on the simulated playback clock | Depends on both the onset detector and the playback policy; can be absent when no onset is detected | +| `underruns` | Later arrival events that exceed the simulated playback deadline | Event count, not total missing-audio duration or measured device underruns | +| `audio_s` | Complete received PCM sample count divided by sample rate | Delivered content duration; preserve it alongside latency and completion | + +The client's zero-buffer simulation starts playback at the first complete +payload arrival. Each payload extends the deadline by its audio duration. If a +later payload arrives after that deadline, the simulation records an underrun +and restarts playback at the later arrival before adding its duration. Audible +onset uses this rebased clock, rather than adding leading silence directly to +first-body time. [Playback calculation][playback] + +Retain the onset detector's parameters when comparing audible latency. This +source uses 20 ms RMS frames, 10 ms hops, per-frame DC removal, a -45 dBFS +threshold and two consecutive active frames. These are the source's detector +settings, not general quality or acceptance gates. Its tests define an onset +case and a late-arrival case; they are test definitions, not executed audio or +service evidence. [Detector][detector] · [Client test definitions][client-tests] + +If a supplied report records only HTTP headers, token events or first-body +time, keep first-playable/audible latency unknown until the required event is +available. Do not infer physical playback from this simulation. + +## 2. Separate server credit from client playback + +Trace the actual PCM bytes credited by the serving path before interpreting a +deadline scheduler. Here, each session retains its first route timestamp and +accumulates routed sample duration. The scheduler estimates its playback +deadline as that timestamp plus the accumulated duration. +[Session accounting][session] · [Deadline policy][scheduler] + +The generator marks credit immediately before yielding a nonempty encoded, +optionally trimmed PCM payload. This is the server response-generator boundary; +it is not acknowledgment of network receipt or client consumption. The server's +monotonic clock and the client's request-relative arrival/playback clock must +remain distinct. No client buffer feedback is present in these selected paths. +[PCM production and credit][route] + +The source prioritizes established streams within its configured reserve, +then streams without a first PCM payload, then established streams with the +earliest estimated deadline, with admission order resolving ties. The default +reserve is 100 ms in this source. Treat it as source context, not a universal +bar or a guarantee that a client will avoid underruns. Record actual arrival +and playback observations before claiming continuity. [Policy][scheduler] · +[CLI conversion and validation][arguments] + +When leading-silence trimming is enabled, initial output can be buffered and +released only after its bounded onset/buffer decision. Credit uses the resulting +payload length. Record trimming, pre-roll and startup-buffer settings with both +first-payload and audible measurements. Changing initial PCM content does not +establish reduced model computation or a latency benefit for every request. +[Trimmer][detector] · [Documented scope][trim] + +## 3. Identify independent batching work and accumulated cost + +Inspect the selected planner and session state before treating chunks as +independent jobs. For this model, the first non-final hop includes prompt-token +alignment padding and requires lookahead tokens; lookahead is resent without +being consumed. Later hops grow to the configured cap, and completion drains +the remaining tokens. Nominal hop size alone does not identify the delivered +PCM duration. Use actual output samples for playback credit. +[Chunk planning][planner] · [Model rates][builders] + +The serving coroutine awaits each session's submitted chunk. The packed worker +also allows at most one chunk from a given session in a batch because the next +chunk depends on that session's Mel cache. It forms batches from ready jobs +across different sessions, subject to its maximum size and scheduling order. +This is the source's dependency boundary, not proof that an arbitrary caller's +jobs or changed model are independent. [Submission][route] · [Worker][worker] + +Flow runs across the selected sessions, after which HiFT finishes each session +separately. Each finish updates accumulated Mel state, vocodes that cache and +returns only waveform samples beyond the previous speech offset. The visible +streaming path also recomputes Flow from the available token prefix. Newly +delivered audio is therefore not a measure of all work performed for that +chunk. [Token2Wav implementation][token2wav] + +When auditing a batching or chunk-size claim, retain prompt and lookahead +context, prefix length, accumulated Mel length, actual batch membership and +per-session output duration. Keep queueing, conditioning, vocoding, conversion +and delivery in the declared cost boundary. A packed Flow call does not show +batched HiFT, constant work per emitted chunk, numerical parity or a service +throughput gain. Queue tests using fake workers define selection/dependency +cases only; no native model result follows from them. [Worker test definitions][worker-tests] + +## 4. Audit the reported timing and quality boundary + +Resolve registered-voice and reference-cache state before comparing cost. A +registered voice reuses prepared conditions; a request-level reference follows +audio decoding/frontend processing and can itself hit the frontend cache. +Record which preparation actually belongs to the timed request. +[Condition resolution][condition] · [Frontend cache][frontend] + +| Source measurement or mode | Included boundary | Required interpretation | +| --- | --- | --- | +| Streaming `request_done.ttfa_ms` | Generator-local start through its first nonempty PCM payload | The streaming HTTP handler resolves conditioning before this timer starts; it excludes that earlier preparation and client delivery | +| `stream=false` HTTP response | The same incremental synthesis collected before response delivery | It changes buffering, not the backend into the separate offline static-batch implementation; internal route credit does not observe buffered-response playback | +| Offline `rtf` | Sum of LLM and Token2Wav stage wall times divided by token-derived audio seconds | Frontend time is reported separately; loading, other preparation and output delivery are not a full-pipeline denominator | +| Offline `audio_seconds` | Counted generated token IDs divided by the source's 25-token/s rate | Not measured saved/received PCM duration; the counter is updated before filtering outputs without valid speech tokens | +| Documented RTFx | Audio duration received within a measurement window divided by window duration | Author-reported aggregate throughput; do not replace it with inverse mean per-request RTF or the offline estimate | + +Source paths: [HTTP handler][handler], [generator timer][route], +[offline accounting][offline] and [reported metrics][benchmark]. Keep an absent +common timing or audio-duration boundary unresolved rather than comparing +similarly named fields. + +The author performance report uses a fixed registered voice/reference, one +NVIDIA Hopper GPU, fixed concurrency, 15 s warmup, a 60 s measurement window, +seed 0 and disabled trimming. Its concurrency-one cumulative ablations report +complete requests without underruns and equal 760 ms first chunks. Preserve +these conditions when citing the report; the exact Hopper SKU, raw timing +records and independent reproduction are not established here. +[Reported workload][reported] · [Ablation conditions][benchmark] + +The quality table reports a target-only versus DSpark comparison over 2,020 +paired Chinese Seed-TTS samples decoded with Paraformer. It does not establish +speaker similarity, perceptual quality, every cumulative optimization's quality +or another workload's result. Keep its character-error protocol and per-row +conditioning scope distinct from fixed-voice performance. The inspected release +tree contains no raw benchmark/evaluator receipts; that does not establish +whether external receipts exist. [Author quality report][quality] + +Return a benchmark contract or audit note identifying the event/buffer policy, +server-credit origin, dependent state, actual timed stages, delivered-duration +denominator, quality scope and missing evidence. If a required event, native +dispatch, output, evaluator or common boundary is missing, withhold the affected +comparison or gain claim. Use the parent method's frozen gates and verdicts for +any separately authorized campaign. + +## Source and rights limits + +The pinned tree has no repository-level license/notice file and its package +metadata declares no license, so overall source rights remain **UNKNOWN**. +Selected NVIDIA and Alibaba files have Apache-2.0 headers; those do not license +other files. The vendored HiFT generator names unpinned HiFi-GAN, +ParallelWaveGAN and BigVGAN origins, and Nari-compatible comments do not resolve +implementation lineage. Exact header scopes, unresolved inheritance and other +unlicensed files remain in the [source record](faster-cosyvoice-source.json). + +This reference contains original analysis and immutable links. It copies no +upstream implementation, patch, audio, model, dataset, paper or figure. Source +dependency/model names are inspection context, not a tested stack or permission +to install or execute it. Recheck changed source contracts before transferring +the procedure; no native, quality, performance or efficacy result is implied. + +[source]: https://github.com/yuekaizhang/faster-cosyvoice/tree/f1049c59196c2c1a890079abc56056b43f27cd1d +[client]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/examples/stream_client.py#L85-L134 +[playback]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/examples/stream_client.py#L27-L51 +[detector]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/leading_silence.py#L1-L88 +[client-tests]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/tests/test_stream_client.py#L6-L22 +[session]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/session.py#L17-L37 +[scheduler]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/token2wav_scheduler.py#L46-L122 +[route]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/openai_speech.py#L52-L128 +[arguments]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/arguments.py#L273-L336 +[trim]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/usage.md#L198-L202 +[planner]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/chunker.py#L20-L55 +[builders]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/builders.py#L16-L50 +[worker]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/token2wav_batcher.py#L79-L183 +[token2wav]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/token2wav.py#L153-L226 +[worker-tests]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/tests/test_token2wav_batcher.py#L57-L320 +[condition]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/openai_speech.py#L31-L49 +[frontend]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/frontend.py#L91-L139 +[handler]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/app.py#L143-L173 +[offline]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/examples/offline_inference.py#L240-L308 +[benchmark]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/benchmark.md#L9-L49 +[reported]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/README.md#L120-L135 +[quality]: https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/benchmark.md#L74-L84 diff --git a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json new file mode 100644 index 000000000..d250c0920 --- /dev/null +++ b/src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/faster-cosyvoice-source.json @@ -0,0 +1,776 @@ +{ + "schema_version": 1, + "record_kind": "source-readset", + "source": { + "type": "git", + "url": "https://github.com/yuekaizhang/faster-cosyvoice", + "repository": "yuekaizhang/faster-cosyvoice", + "commit": "f1049c59196c2c1a890079abc56056b43f27cd1d", + "tree": "a5950f9eaa500141d08c29e29dc24e8d1f313f00", + "tree_entries": 117, + "truncated": false + }, + "inspected_at": "2026-11-03", + "status": "candidate", + "empirical_validation": "not_run", + "efficacy": "not_evaluated", + "scope": "Bounded source-only interpretation of PCM receipt/playout, server route credit, dependency-limited cross-session batching and partial pipeline/audio denominators; author performance and DSpark quality reports remain separate from execution.", + "access_and_identity": "Read-only GitHub connector commit/tree/file calls, with per-file blob identity checked against the complete pinned tree", + "rights": { + "repository_license": "UNKNOWN", + "pinned_tree_license_notice_paths": [], + "pyproject_license_declaration": "absent", + "no_default_branch_license_inference": true, + "file_headers_are_not_repository_license": true, + "redistribution_boundary": "Only original explanatory analysis and immutable links are proposed. No source implementation, patches, audio, models, datasets, papers, screenshots or figures are copied or adapted. Unpinned inherited provenance remains unresolved." + }, + "readset": [ + { + "path": "README.md", + "git_blob_sha": "131c56b961e0cb045997df712ffe314cdf4ef957", + "tree_size_bytes": 5675, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 147 + ] + ], + "role": "Source overview, reported fixed-registered-voice benchmark and acknowledgments", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/README.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "README_zh.md", + "git_blob_sha": "a93f11ca7ac90ea736af78ffc12b3f83a8225fe2", + "tree_size_bytes": 5398, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 36 + ], + [ + 124, + 124 + ] + ], + "role": "Bounded Chinese counterpart overview and attribution cross-check", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/README_zh.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "docs/benchmark.md", + "git_blob_sha": "a4d127435287776df29b90019dd6878a0e8e209b", + "tree_size_bytes": 3574, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 84 + ] + ], + "role": "Author-reported metric, workload, cumulative ablation and DSpark-only CER scope", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/benchmark.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "docs/benchmark_zh.md", + "git_blob_sha": "8c9d1c9fa5a48173b14628ad0849bdc975c1abe0", + "tree_size_bytes": 3161, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 76 + ] + ], + "role": "Chinese counterpart metric/workload/quality cross-check", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/benchmark_zh.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "docs/usage.md", + "git_blob_sha": "46cf5bb01c7d6bad93219866a5050b4039e21c76", + "tree_size_bytes": 8103, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 228 + ] + ], + "role": "Documented API modes, conditioning cache, chunk/graph/trim scopes and CLI defaults", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/usage.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "docs/usage_zh.md", + "git_blob_sha": "328a4b2c587415a4dd733a22b0a13b08e9a0c3c2", + "tree_size_bytes": 7498, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 78, + 95 + ], + [ + 160, + 205 + ] + ], + "role": "Bounded Chinese counterpart API, graph-duration and trim cross-check", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/docs/usage_zh.md", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "examples/offline_inference.py", + "git_blob_sha": "ab98b25448cd0d61f76439799dab5947b850cb86", + "tree_size_bytes": 14364, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 100 + ], + [ + 150, + 321 + ] + ], + "role": "Selected per-row provenance, stage timing and token-derived audio/RTF denominator; loader/CLI lines 101-149 excluded", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/examples/offline_inference.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "examples/stream_client.py", + "git_blob_sha": "491c8e9e0de7d619839c01a274fe73c0b27ae243", + "tree_size_bytes": 4833, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 142 + ] + ], + "role": "PCM16 sample reconstruction, client event clocks and zero-buffer playback diagnostics", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/examples/stream_client.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/config/settings.py", + "git_blob_sha": "fa5a4fb7e5936deeb94ea295602b014ee9574c62", + "tree_size_bytes": 3127, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 79 + ] + ], + "role": "Typed source defaults and optional feature scopes", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/config/settings.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/llm/engine.py", + "git_blob_sha": "8ecae2c648f6709e3163ca6d0bc94a48d60903ae", + "tree_size_bytes": 5294, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 14, + 141 + ] + ], + "role": "Selected draft configuration dependency, token deltas and source length-stop warning; no upstream vLLM runtime validation", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/llm/engine.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/app.py", + "git_blob_sha": "91a917ba12f8d45a5457eeed74b94b9b39a01bb5", + "tree_size_bytes": 8000, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 212 + ] + ], + "role": "Initialization and shared objects, condition resolution, streaming/buffered response and voice-cache paths", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/app.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/arguments.py", + "git_blob_sha": "126514f5c3a7df3a93900201e21a68482b631aeb", + "tree_size_bytes": 11598, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 115 + ], + [ + 195, + 336 + ] + ], + "role": "Selected effective CLI defaults, estimator/batch validation and parameter-to-runtime conversion", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/arguments.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/audio_encode.py", + "git_blob_sha": "76f7dd30ea10beb7a4a1b838002aae692c888706", + "tree_size_bytes": 970, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 36 + ] + ], + "role": "PCM16 encoding and header-only WAV prefix boundary", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/audio_encode.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/leading_silence.py", + "git_blob_sha": "ee2303e377f96dbbcd4803a038b1e04d18a78d7e", + "tree_size_bytes": 3741, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 88 + ] + ], + "role": "Declared onset rule and bounded content buffering/trimming; attributed Nari origin not independently source-matched", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/leading_silence.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/openai_speech.py", + "git_blob_sha": "6f937211c5327c19de847943255c9dd40adda214", + "tree_size_bytes": 5751, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 137 + ] + ], + "role": "Condition/prompt/token/chunk pipeline and routed-PCM credit publication", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/openai_speech.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/server/protocol.py", + "git_blob_sha": "0abd7892098b17c0e1ae323a765b29e6176fd6df", + "tree_size_bytes": 3222, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 98 + ] + ], + "role": "Request format/mode fields and reference audio decoding boundary", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/server/protocol.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/streaming/chunker.py", + "git_blob_sha": "c0d202f1d8fe577bf4cfc83946c4090d9eb97234", + "tree_size_bytes": 2255, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 55 + ] + ], + "role": "Initial prompt-alignment padding, lookahead, growing hops and final remainder", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/chunker.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/streaming/session.py", + "git_blob_sha": "7bbb690e1e59fff0ae0a1e5315a0aeaab6a00205", + "tree_size_bytes": 1351, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 37 + ] + ], + "role": "Session-owned Mel/audio state and route-origin audio credit", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/session.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "Names Nari or vLLM-derived/compatible behavior without pinned source lineage; this does not grant copying rights" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/streaming/token2wav_batcher.py", + "git_blob_sha": "12dccc32558f84c34ecd440943ff46baae2947e5", + "tree_size_bytes": 7552, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 183 + ] + ], + "role": "Ready-job selection, one GPU thread, one chunk per session in packed batches and pending/failure behavior", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/token2wav_batcher.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/streaming/token2wav_scheduler.py", + "git_blob_sha": "4324eac7bfaaa5fc125c695339c05d1ef7ea209b", + "tree_size_bytes": 4553, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 137 + ] + ], + "role": "Server-estimated playback deadline and urgent/startup/earliest/FIFO queue ordering", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/streaming/token2wav_scheduler.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/builders.py", + "git_blob_sha": "9d774feefa3f8bcb9d6b61c4aba96894d0c4040f", + "tree_size_bytes": 2491, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 50 + ] + ], + "role": "Model-local token/Mel/sample rates and component dependency identities", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/builders.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/cosyvoice/flow/DiT/modules.py", + "git_blob_sha": "be8caecb8a2acd290f4f6e7e1d756dff67f78e5b", + "tree_size_bytes": 20551, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": { + "first_line": 1, + "last_line": 55 + }, + "inspected_ranges": [ + [ + 1, + 55 + ] + ], + "role": "Header/import scan only; source lineage and whole-file rights unresolved", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/cosyvoice/flow/DiT/modules.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/cosyvoice/flow/flow.py", + "git_blob_sha": "a00e2d1a7ff6fc6cf7627f64fabf544ff54b47e4", + "tree_size_bytes": 19346, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": { + "first_line": 1, + "last_line": 45 + }, + "inspected_ranges": [ + [ + 1, + 45 + ] + ], + "role": "File-level rights/header and dependency declaration only; algorithm body excluded", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/cosyvoice/flow/flow.py", + "rights": { + "license": "Apache-2.0 file header observed", + "copyright": "2024 Alibaba Inc; authors Xiang Lyu, Zhihao Du", + "exception": "Only lines 1-45 inspected; deeper inherited material and modifications not separately rights-audited" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/cosyvoice/hifigan/generator.py", + "git_blob_sha": "53344d78dfbfded36da1f79f12d886e14a659aa0", + "tree_size_bytes": 30935, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": { + "first_line": 1, + "last_line": 45 + }, + "inspected_ranges": [ + [ + 1, + 45 + ] + ], + "role": "File-level rights and unpinned HiFi-GAN/ParallelWaveGAN/BigVGAN attribution only; algorithm body excluded", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/cosyvoice/hifigan/generator.py", + "rights": { + "license": "Apache-2.0 file header observed", + "copyright": "2024 Alibaba Inc; authors Xiang Lyu, Kai Hu", + "exception": "Lines 39-41 identify modifications from HiFi-GAN, ParallelWaveGAN and BigVGAN without pins; those inherited rights are unresolved, not replaced by the outer header" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/flashinfer_dit.py", + "git_blob_sha": "2fc3bb419dd421d21d1f5a892bffbf1602c5f09c", + "tree_size_bytes": 39248, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": { + "first_line": 1, + "last_line": 95 + }, + "inspected_ranges": [ + [ + 1, + 95 + ] + ], + "role": "Header, imports and class declarations only; no kernel, graph dispatch or mask-correctness audit", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/flashinfer_dit.py", + "rights": { + "license": "Apache-2.0 file header observed", + "copyright": "2026 NVIDIA CORPORATION", + "exception": "Only lines 1-95 inspected; no repository-wide license or full body/lineage audit" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/flashinfer_flow.py", + "git_blob_sha": "a51f2991e7960d2b70fa4e2296f2dc2cdb321acb", + "tree_size_bytes": 11048, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 110 + ], + [ + 207, + 319 + ] + ], + "role": "Header and selected packed streaming interface/returned per-request Mel lengths; middle helpers excluded", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/flashinfer_flow.py", + "rights": { + "license": "Apache-2.0 file header observed", + "copyright": "2026 NVIDIA CORPORATION", + "exception": "Copyright/license notice search across complete retrieved file found only the header; algorithm review limited to declared ranges" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/frontend.py", + "git_blob_sha": "7df23a44301baad34a47b45d74c5db8742cfced4", + "tree_size_bytes": 6021, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 146 + ] + ], + "role": "Reference token/features/speaker conditions, cache-hit and per-request preparation cost", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/frontend.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/matcha_audio.py", + "git_blob_sha": "d257f0d652822851714c47826dc4b1b69fb09fcd", + "tree_size_bytes": 2311, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": { + "first_line": 1, + "last_line": 45 + }, + "inspected_ranges": [ + [ + 1, + 45 + ] + ], + "role": "Header/import scan only; whole-file rights/lineage unresolved", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/matcha_audio.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "faster_cosyvoice/token2wav/token2wav.py", + "git_blob_sha": "7afdc1c6dd002d0c5757bbadeec880644c8b9e34", + "tree_size_bytes": 11040, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 226 + ] + ], + "role": "Single/packed Flow execution boundary, cumulative Mel vocoding and newly emitted CPU waveform slice", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/faster_cosyvoice/token2wav/token2wav.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "pyproject.toml", + "git_blob_sha": "5a3d8a1ced57a487bdb1b25a30d42ed852711c18", + "tree_size_bytes": 1690, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 59 + ] + ], + "role": "Dependency/build/source revision constraints and absent project-license declaration", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/pyproject.toml", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "tests/test_session.py", + "git_blob_sha": "9623c8c473542e3223830a288d0cf6d33314eaf8", + "tree_size_bytes": 710, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 18 + ] + ], + "role": "Source test definition for cumulative routed-sample accounting, not executed", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/tests/test_session.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "tests/test_stream_client.py", + "git_blob_sha": "235ae7f74e20284ff9de7b79c152f3263ff87889", + "tree_size_bytes": 848, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 22 + ] + ], + "role": "Source test definitions for audible onset and one late arrival, not executed", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/tests/test_stream_client.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + }, + { + "path": "tests/test_token2wav_batcher.py", + "git_blob_sha": "80f3fb580a947929bace3a32fb109dd5c65eb031", + "tree_size_bytes": 10630, + "identity_matches_complete_pinned_tree": true, + "retrieval_scope": "complete_file", + "inspected_ranges": [ + [ + 1, + 320 + ] + ], + "role": "Source test definitions using fake workers for queueing/dependency/cancellation/error contracts, not executed or native qualification", + "immutable_url": "https://github.com/yuekaizhang/faster-cosyvoice/blob/f1049c59196c2c1a890079abc56056b43f27cd1d/tests/test_token2wav_batcher.py", + "rights": { + "license": "UNKNOWN", + "copyright": "No explicit copyright notice in retrieved material", + "exception": "No repository-level license at the pinned tree; no license inference from dependencies, file path or default branch" + }, + "copy_action": "reference_only; original analysis; no upstream code or media copied" + } + ], + "exclusions": [ + "All docs/assets SVG bodies and any chart extraction/reproduction", + "uv.lock dependency body (tree identity only)", + "GPU/native test bodies; no upstream test execution", + "Actual CUDA, FlashInfer, Triton, vLLM fork execution and numerical/dispatch qualification", + "Target/draft/Flow/HiFT/model downloads, audio/data, speaker verification, listening or ASR evaluation", + "Uninspected algorithm portions of vendor files and FlashInfer DiT; no copied implementation or presumed inherited rights", + "Repositories outside this source, including dependencies and acknowledged implementations; their names do not establish inspected lineage or inherited copying rights" + ], + "evidence_limits": { + "source_observation": "Selected source text and code contracts only", + "deduction": "Measurement/ownership implications are labeled separately", + "author_report": "Benchmark and DSpark CER report only", + "cpu_execution": "not_run", + "device_execution": "not_run", + "quality": "not_run", + "service_performance": "not_run", + "efficacy": "not_evaluated" + } +}