Skip to content

Actions: 1CatAI/1Cat-vLLM

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
1,675 workflow runs
1,675 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[Bugfix] PLE offload: send registration inputs by file descriptor pre-commit #1738: Pull request #654 opened by Peuqui
6m 5s Peuqui:ple-registration-fd-sharing
Peuqui:ple-registration-fd-sharing
6m 5s
[Bugfix] Constrain tools + response_format with a union grammar in Qwen3XMLToolParser pre-commit #1737: Pull request #653 opened by areslp
8s areslp:fix/qwen3xml-tools-with-response-format
areslp:fix/qwen3xml-tools-with-response-format
8s
[Model][SM70] Accept DFlash embed replica across split load_weights c… pre-commit #1736: Pull request #651 opened by ProprietaryLegal
Action required ProprietaryLegal:fix/glm53-dflash-embed-replica-multicall
ProprietaryLegal:fix/glm53-dflash-embed-replica-multicall
Action required
[Bugfix][SM70] Stop grouped-page4 null-block padding from leaking E4M3 NaN pre-commit #1735: Pull request #647 synchronize by areslp
12s areslp:fix/sm70-grouped-page4-null-block-padding-nan
areslp:fix/sm70-grouped-page4-null-block-padding-nan
12s
[Bugfix][SM70] Stop grouped-page4 null-block padding from leaking E4M3 NaN pre-commit #1734: Pull request #647 opened by areslp
9s areslp:fix/sm70-grouped-page4-null-block-padding-nan
areslp:fix/sm70-grouped-page4-null-block-padding-nan
9s
[Feature][Qwen4Exp] PLE overflow cascade: device, pinned host, spare GPU, disk pre-commit #1733: Pull request #646 opened by Peuqui
6m 17s Peuqui:qwen4exp-ple-tier-cascade-pr
Peuqui:qwen4exp-ple-tier-cascade-pr
6m 17s
Merge pull request #645 from 1CatAI/codex/v100-75t-prefix-bridge-2026… pre-commit #1732: Commit b711d53 pushed by yangzhuxinyzx
5m 22s main
main
5m 22s
[Core][SM70] Decouple the Mamba state grid from the KV block size pre-commit #1731: Pull request #645 synchronize by yangzhuxinyzx
11m 40s codex/v100-75t-prefix-bridge-20260916
codex/v100-75t-prefix-bridge-20260916
11m 40s
[Core][SM70] Decouple the Mamba state grid from the KV block size pre-commit #1730: Pull request #645 opened by yangzhuxinyzx
5m 52s codex/v100-75t-prefix-bridge-20260916
codex/v100-75t-prefix-bridge-20260916
5m 52s
[Perf][SM70] Pace chunked prefill and unpin the D256 BM32 page size (#490) pre-commit #1729: Pull request #616 synchronize by areslp
10s areslp:fix/sm70-mixed-batch-decode-rows
areslp:fix/sm70-mixed-batch-decode-rows
10s
[Bugfix][Qwen4Exp] Detect the FP8 PLE table from ModelOpt mixed-precision configs pre-commit #1728: Pull request #640 opened by Peuqui
5m 53s Peuqui:qwen4exp-ple-fp8-modelopt-mixed
Peuqui:qwen4exp-ple-fp8-modelopt-mixed
5m 53s
[Bugfix][Qwen4Exp] Allow checkpoint FP8 MTP experts under pipeline parallelism pre-commit #1727: Pull request #639 opened by Peuqui
6m 17s Peuqui:qwen4exp-fp8-mtp-experts-pp
Peuqui:qwen4exp-fp8-mtp-experts-pp
6m 17s
[Core][SM70] Beat A800 C32 decode and recover 32K serving pre-commit #1726: Pull request #629 synchronize by yangzhuxinyzx
4m 6s codex/v100-27b-fp8-c32-plus10-20260914
codex/v100-27b-fp8-c32-plus10-20260914
4m 6s
Merge pull request #638 from 1CatAI/codex/v100-fp8kv-fp16-route-parit… pre-commit #1725: Commit 02c87ab pushed by yangzhuxinyzx
7m 26s main
main
7m 26s
[Kernel][SM70] Share FP16 attention fast paths with E4M3 KV pre-commit #1724: Pull request #638 synchronize by yangzhuxinyzx
5m 0s codex/v100-fp8kv-fp16-route-parity-20260914-122513
codex/v100-fp8kv-fp16-route-parity-20260914-122513
5m 0s
[Perf][SM70] Block-pack the activations of the NVFP4 QPN2 kernels pre-commit #1723: Pull request #611 synchronize by Peuqui
7m 24s Peuqui:sm70-qpn2-block-pack-pr
Peuqui:sm70-qpn2-block-pack-pr
7m 24s
[Kernel][SM70] Share FP16 attention fast paths with E4M3 KV pre-commit #1722: Pull request #638 synchronize by yangzhuxinyzx
6m 35s codex/v100-fp8kv-fp16-route-parity-20260914-122513
codex/v100-fp8kv-fp16-route-parity-20260914-122513
6m 35s
[Kernel][SM70] Share FP16 attention fast paths with E4M3 KV pre-commit #1721: Pull request #638 synchronize by yangzhuxinyzx
7m 23s codex/v100-fp8kv-fp16-route-parity-20260914-122513
codex/v100-fp8kv-fp16-route-parity-20260914-122513
7m 23s
[Kernel][SM70] Share FP16 attention fast paths with E4M3 KV pre-commit #1720: Pull request #638 synchronize by yangzhuxinyzx
7m 25s codex/v100-fp8kv-fp16-route-parity-20260914-122513
codex/v100-fp8kv-fp16-route-parity-20260914-122513
7m 25s
[Kernel][SM70] Share FP16 attention fast paths with E4M3 KV pre-commit #1719: Pull request #638 opened by yangzhuxinyzx
7m 54s codex/v100-fp8kv-fp16-route-parity-20260914-122513
codex/v100-fp8kv-fp16-route-parity-20260914-122513
7m 54s
[Bugfix][MRV2] Backport phase-aware decode graph dispatch pre-commit #1718: Pull request #637 opened by Leonccaa
7m 21s Leonccaa:fix/mrv2-prefill-decode-dispatch
Leonccaa:fix/mrv2-prefill-decode-dispatch
7m 21s
[Bugfix][Qwen3.5] Keep the MTP drafter stage-local under pipeline parallelism pre-commit #1717: Pull request #636 opened by Peuqui
8s Peuqui:qwen3-5-mtp-pp
Peuqui:qwen3-5-mtp-pp
8s
Merge pull request #635 from 1CatAI/codex/v100-79t-q8192-concurrency-… pre-commit #1716: Commit a6f5e83 pushed by yangzhuxinyzx
6m 54s main
main
6m 54s
[Kernel] Expand SM70 75T prefill to Q8192 and concurrent requests pre-commit #1715: Pull request #635 opened by yangzhuxinyzx
7m 24s codex/v100-79t-q8192-concurrency-20260914
codex/v100-79t-q8192-concurrency-20260914
7m 24s
[Core][SM70] Beat A800 C32 decode and recover 32K serving pre-commit #1714: Pull request #629 synchronize by yangzhuxinyzx
7m 51s codex/v100-27b-fp8-c32-plus10-20260914
codex/v100-27b-fp8-c32-plus10-20260914
7m 51s