[harvest] feat(convert): rebase MLA LoRA conversion - #169
Open
marksverdhai wants to merge 336 commits into
Open
Conversation
* CUDA: Fuse MMVQ for NVFP4 and BS 1 TODO: 1. Add tests to test-backend-ops (did verify correctness manually for one model) 2. Reorder bias/scale once PRs for NVFP4 are merged/landed * Add dense MMVQ fusion as well Perf numbers on B4500. Note qwen35 is FP8->Q8 + ./scripts/compare-llama-bench.py -b master -c osimons/nvfp4_fuse_mmvq --tool llama-bench -i llama-bench.sqlite | Model | Test | t/s master | t/s osimons/nvfp4_fuse_mmvq | Speedup | |:-------------------------|:-------------|-------------:|------------------------------:|----------:| | qwen35moe 35B.A3B NVFP4 | tg128@d32768 | 150.15 | 156.29 | 1.04 | | qwen35moe 35B.A3B Q4_K_M | tg128@d32768 | 157.91 | 157.64 | 1.00 | Perf numbers on DGX Spark + ./scripts/compare-llama-bench.py -b master -c osimons/nvfp4_fuse_mmvq --tool llama-bench -i llama-bench.sqlite | Model | Test | t/s master | t/s osimons/nvfp4_fuse_mmvq | Speedup | |:-------------------------|:-------------|-------------:|------------------------------:|----------:| | qwen35moe 35B.A3B NVFP4 | tg128@d32768 | 58.31 | 59.69 | 1.02 | | qwen35moe 35B.A3B Q4_K_M | tg128@d32768 | 54.94 | 54.79 | 1.00 | * Add tests for the added fusion ops * Cleanup test-backend-ops * Cleanup ggml-cuda/mmvq 1. Unrestrict post-scale fusion 2. Rename names accordingly 3. Remove env variable to disable fusion * Merge old mul_mat patterns into the lane-based approach * Enable fusion for MoE in shared MMVQ * Restrict scale_view_nodes, enroll MM + ADD into lane-matcher * Refactor mmvq loads, still does not help non-nvfp4 kernels * Restrict scale-fusion to NVFP4 This is necessary, as the prolog is quite heavy in GEMV for some quants/model configs, leading to net perf regression. We should really be looking to refactor this such that ratio of prologue/hot-loop/epilogue is better on the hot-loop front: + ./scripts/compare-llama-bench.py -b master -c c1b9381 --tool llama-bench -i llama-bench.sqlite | CPU | Model | Test | t/s master | t/s c1b9381 | Speedup | |:----------------------------|:-------------------------|:-------------|-------------:|----------------:|----------:| | INTEL(R) XEON(R) GOLD 6542Y | gemma4 26B.A4B NVFP4 | tg128@d32768 | 151.70 | 154.32 | 1.02 | | INTEL(R) XEON(R) GOLD 6542Y | gemma4 26B.A4B Q4_K_M | tg128@d32768 | 187.95 | 185.73 | 0.99 | | INTEL(R) XEON(R) GOLD 6542Y | gpt-oss 20B MXFP4 MoE | tg128@d32768 | 304.62 | 300.69 | 0.99 | | INTEL(R) XEON(R) GOLD 6542Y | qwen35moe 35B.A3B NVFP4 | tg128@d32768 | 193.72 | 211.99 | 1.09 | | INTEL(R) XEON(R) GOLD 6542Y | qwen35moe 35B.A3B Q4_K_M | tg128@d32768 | 217.76 | 218.15 | 1.00 * Reorder scale & bias-add to adhere to ggml-org#24331 * Restrict lane scale to NVFP4 Don't need to test unfused combinations * Cleanup * Merge single-lane mm-fusion helpers * Refactor and clean-up host-side fusion logic * Move gate_bias and scale into the same active-thread guard Latest perf numbers: B6000 build: 5b7d9f272 (9578) + ./scripts/compare-llama-bench.py -b master -c osimons/nvfp4_fuse_mmvq --tool llama-bench -i llama-bench.sqlite | CPU | Model | Test | t/s master | t/s osimons/nvfp4_fuse_mmvq | Speedup | |:----------------------------|:-------------------------|:-------------|-------------:|------------------------------:|----------:| | INTEL(R) XEON(R) GOLD 6542Y | gemma4 26B.A4B NVFP4 | tg128@d32768 | 151.79 | 154.10 | 1.02 | | INTEL(R) XEON(R) GOLD 6542Y | gemma4 26B.A4B Q4_K_M | tg128@d32768 | 187.90 | 187.27 | 1.00 | | INTEL(R) XEON(R) GOLD 6542Y | gpt-oss 20B MXFP4 MoE | tg128@d32768 | 303.77 | 306.56 | 1.01 | | INTEL(R) XEON(R) GOLD 6542Y | qwen35moe 35B.A3B NVFP4 | tg128@d32768 | 193.41 | 207.99 | 1.08 | | INTEL(R) XEON(R) GOLD 6542Y | qwen35moe 35B.A3B Q4_K_M | tg128@d32768 | 217.60 | 218.58 | 1.00 | DGX Spark build: 5b7d9f272 (9578) + ./scripts/compare-llama-bench.py -b master -c osimons/nvfp4_fuse_mmvq --tool llama-bench -i llama-bench.sqlite | CPU | Model | Test | t/s master | t/s osimons/nvfp4_fuse_mmvq | Speedup | |:------|:-------------------------|:-------------|-------------:|------------------------------:|----------:| | CPU | gemma4 26B.A4B NVFP4 | tg128@d32768 | 34.61 | 34.84 | 1.01 | | CPU | gemma4 26B.A4B Q4_K_M | tg128@d32768 | 46.95 | 46.90 | 1.00 | | CPU | gpt-oss 20B MXFP4 MoE | tg128@d32768 | 64.84 | 64.62 | 1.00 | | CPU | qwen35moe 35B.A3B NVFP4 | tg128@d32768 | 59.63 | 60.72 | 1.02 | | CPU | qwen35moe 35B.A3B Q4_K_M | tg128@d32768 | 56.53 | 56.55 | 1.00 | PPL values for 5 chunks: this PR model mode ppl uncertainty log /mnt/share/gguf/unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf fusion_enabled 5.2892 0.35389 ppl-value-checks/Qwen3.6-35B-A3B-UD-Q4_K_M.fusion_enabled.log /mnt/share/gguf/unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf fusion_disabled 5.2742 0.35215 ppl-value-checks/Qwen3.6-35B-A3B-UD-Q4_K_M.fusion_disabled.log /mnt/share/gguf/nvidia/Qwen3.6-35B-A3B-2.06GB-per-token-CT/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.gguf fusion_enabled 5.4487 0.36866 ppl-value-checks/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.fusion_enabled.log /mnt/share/gguf/nvidia/Qwen3.6-35B-A3B-2.06GB-per-token-CT/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.gguf fusion_disabled 5.4403 0.36782 ppl-value-checks/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.fusion_disabled.log /mnt/share/gguf/nvidia/Gemma-4-26B-A4B-NVFP4/Gemma-4-26B-A4B-NVFP4_fp8_q8.gguf fusion_enabled 17342.4348 3703.13932 ppl-value-checks/Gemma-4-26B-A4B-NVFP4_fp8_q8.fusion_enabled.log /mnt/share/gguf/nvidia/Gemma-4-26B-A4B-NVFP4/Gemma-4-26B-A4B-NVFP4_fp8_q8.gguf fusion_disabled 18627.0624 3998.42475 ppl-value-checks/Gemma-4-26B-A4B-NVFP4_fp8_q8.fusion_disabled.log /mnt/share/gguf/ggml-org/gpt-oss-20b-GGUF/gpt-oss-20b-mxfp4.gguf fusion_enabled 363.8913 33.14007 ppl-value-checks/gpt-oss-20b-mxfp4.fusion_enabled.log /mnt/share/gguf/ggml-org/gpt-oss-20b-GGUF/gpt-oss-20b-mxfp4.gguf fusion_disabled 363.8913 33.14007 ppl-value-checks/gpt-oss-20b-mxfp4.fusion_disabled.log /mnt/share/gguf/unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf fusion_enabled 17330.3926 3716.70472 ppl-value-checks/gemma-4-26B-A4B-it-UD-Q4_K_XL.fusion_enabled.log /mnt/share/gguf/unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf fusion_disabled 17933.9524 3883.17066 ppl-value-checks/gemma-4-26B-A4B-it-UD-Q4_K_XL.fusion_disabled.log master: summary: ppl-value-checks/summary.tsv model mode ppl uncertainty log /mnt/share/gguf/unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf fusion_enabled 5.2892 0.35389 ppl-value-checks/Qwen3.6-35B-A3B-UD-Q4_K_M.fusion_enabled.log /mnt/share/gguf/unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf fusion_disabled 5.2742 0.35215 ppl-value-checks/Qwen3.6-35B-A3B-UD-Q4_K_M.fusion_disabled.log /mnt/share/gguf/nvidia/Qwen3.6-35B-A3B-2.06GB-per-token-CT/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.gguf fusion_enabled 5.4487 0.36866 ppl-value-checks/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.fusion_enabled.log /mnt/share/gguf/nvidia/Qwen3.6-35B-A3B-2.06GB-per-token-CT/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.gguf fusion_disabled 5.4403 0.36782 ppl-value-checks/Qwen3.6-35B-A3B-2.06GB-per-token-CT_fp8_q8.fusion_disabled.log /mnt/share/gguf/nvidia/Gemma-4-26B-A4B-NVFP4/Gemma-4-26B-A4B-NVFP4_fp8_q8.gguf fusion_enabled 17342.4348 3703.13932 ppl-value-checks/Gemma-4-26B-A4B-NVFP4_fp8_q8.fusion_enabled.log /mnt/share/gguf/nvidia/Gemma-4-26B-A4B-NVFP4/Gemma-4-26B-A4B-NVFP4_fp8_q8.gguf fusion_disabled 18627.0624 3998.42475 ppl-value-checks/Gemma-4-26B-A4B-NVFP4_fp8_q8.fusion_disabled.log /mnt/share/gguf/ggml-org/gpt-oss-20b-GGUF/gpt-oss-20b-mxfp4.gguf fusion_enabled 363.8913 33.14007 ppl-value-checks/gpt-oss-20b-mxfp4.fusion_enabled.log /mnt/share/gguf/ggml-org/gpt-oss-20b-GGUF/gpt-oss-20b-mxfp4.gguf fusion_disabled 363.8913 33.14007 ppl-value-checks/gpt-oss-20b-mxfp4.fusion_disabled.log /mnt/share/gguf/unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf fusion_enabled 17330.3926 3716.70472 ppl-value-checks/gemma-4-26B-A4B-it-UD-Q4_K_XL.fusion_enabled.log /mnt/share/gguf/unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf fusion_disabled 17933.9524 3883.17066 ppl-value-checks/gemma-4-26B-A4B-it-UD-Q4_K_XL.fusion_disabled.log * Allow views to weights in ggml_can_fuse_subgraph * Remove gate_first from test_mul_mat_vec_fusion * Ditch lane-parsing approach in favor of hard-coded patterns * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Rename ggml_is_constant_view_src to ggml_is_constant * Finish renaming of 0905129 * Readd descriptive prints for fusion debugging * Add weight-buffer pre-allocation to `test_case` This is required so we correctly test fusion of NVFP4. * Update ggml/src/ggml.c Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * Add 2nd context for weights as suggested by @JohannesGaessler This reflects more natural use of ggml compared to artifically pre-allocating weights into the same context * Exclude fused tests from gradient mode I'm unsure of the current state, but naively every fusion pattern should require its own backpropagation implementation. I don't see these implemented for the CUDA backend, so we can disable tests to avoid triggering GGML_ASSERT for ggml_tensor * build_graph(ggml_context * ctx) override { GGML_ASSERT(!use_weight_context()); return build_graph(ctx, nullptr); } * Apply suggestions from code review Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS * ggml : add missing type checks in f16 GGML_OP_SET_ROWS * ggml : merge ggml_compute_forward_set_rows_f32() and ggml_compute_forward_set_rows_f16() into ggml_compute_forward_set_rows_impl() * chore : replace assert() with GGML_ASSERT() --------- Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
…25390) `simd_gemm()` has an incorrect A-matrix index in the scalar tail-column path for full row blocks.
…-org#18750) * fix: OOB reads in UGM tokenizer (precompiled_charsmap handling) - Validate minimum size (4 bytes) before reading xcda_blob_size - Use strnlen with bounds check instead of unsafe strlen Both issues allow heap-buffer-overflow from malicious T5/UGM GGUF files. * Replace unsafe strnlen() with a bounds-checked loop that scans for \0 within the remaining array size. * move bounds checks to load * typo merge fix --------- Co-authored-by: hourhl <hourhl8200@gmail.com> Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
dict.get("key", default) returns None (not default) when the key
exists but its value is explicitly None. This caused an AttributeError
in _escape_html() when a task errored before grading and answer was
set to None.
Assisted-by: pi:llama.cpp/Qwen3.6-27B
* feat: WIP * feat: Retire ChatScreenProcessingInfo component, context, and keepStatsVisible settings * feat: Always-on gauge with active-model /props, conversation stats and live-reactive reading/output/avg * feat: Add /tokenize endpoint, TokenizeService, FNV-1a and JSON Schema utilities * feat: Surface enabled-tools token count in context hover card * refactor(tools): make toolsStore the sole owner of the OpenAI wire format Previously mcpStore.getToolDefinitionsForLLM() owned the MCP->OpenAI shape conversion (plus normalizeSchemaProperties). That created two sources of truth for what gets sent to the LLM, with the duplication-prone risk of the deduplicated enabled list (which feeds the token-count cache) drifting from the bytes actually shipped on chat. Now: - mcpStore: pure protocol state + routing. Drop getToolDefinitionsForLLM and the inline OpenAIToolDefinition conversion + normalizeSchemaProperties. Doc comment adjusted to declare wire-format ownership as belonging to toolsStore. Connection lifecycle, health checks, executeTool, and the connections/toolsIndex remain. - toolsStore: owns the wire shape (added earlier this series). mcpEntries() inlines the MCP tool conversion; uses normalizeJsonSchema (the JSON Schema util extracted in the prior commit) so missing 'type' fields are inferred from defaults. mcpTools getter iterates mcpEntries() so the Settings UI and the deduplicated enabled list see the same definitions. getEnabledToolsForLLM iterates mcpEntries() instead of calling mcpStore, so the JSON sent to the LLM is identical to what toolsStore.refreshEnabledToolsTokenCount tokenizes. - agentic: the chat-completion tools field's type was annotated as ReturnType<typeof mcpStore.getToolDefinitionsForLLM>, claiming the shape was owned by mcpStore. Switch to ReturnType<typeof toolsStore.getEnabledToolsForLLM>, the actual source. Assisted-by: Claude * feat: UI WIP * feat: UI WIP * feat: UI WIP * feat: Adjust reasoning submenu layout and spacing * feat: Adjust context usage gauge thresholds and styling * feat: Split context usage gauge stats into current and cumulative breakdowns * chore: Format * refactor: Cleanup * refactor: Cleanup * feat: improve token gauge accuracy and display * refactor: remove MCP recommendation gating and simplify server visibility * feat: add token audit logging to ChatStore for debugging * refactor: Simplify context token reading to use server promptTokens directly * feat: Replace last-known token tracking with live server-derived stats for accurate streaming gauges * feat: UI Improvements * feat: Move prompt processing stats to the preceding user message * feat: Fix context token double-counting and refine gauge layout * refactor: remove always-show-agentic-turns setting and simplify agentic turn display * feat: track and display cache tokens in context gauge * feat: add diagnostic logging for chat completion requests * refactor: improve token audit console output with fresh/cached breakdown * fix: invalidate enabled tools token count cache on tool changes * test: add unit tests for tools store token count invalidation * refactor: Remove tools token counting infrastructure * refactor: Update ChatFormContextGauge to use simplified token tracking * refactor: Update ChatStore to remove tools token counting * chore: Formatting * feat: Improve UI text * feat: simplify context usage derivation and refine gauge labels * refactor: cleanup logs * cleaning * fix: UI * refactor: Enums * refactor: Extract context gauge logic into hook and split UI into sub-components * refactor: Cleanup comments --------- Co-authored-by: Pascal <admin@serveurperso.com>
… using the flag benefit (ggml-org#25322)
…org#25047) * server-stream : pimpl * server-stream: prefix free functions with server_stream_ address review from ggerganov: scope the public stream functions under the server_stream_ prefix, matching server_stream_session_manager_start/stop. * server-stream: guard session and manager state with the mutex address review from ggerganov: make done, completed_ts and the GC running flag plain members under their mutex and set the condvar predicates under the lock. keep cancelled atomic for the lock-free should_stop poll. * server-stream: trim comments to the non-obvious address review from ggerganov: drop comments that restate the code, keep the concurrency, lifetime and ordering rationale. de-stale a few comments left by the pimpl: g_stream_sessions is now internal and the /v1/streams listing is gone. * server-stream: update dev docs for the pimpl and prefix reflect server_stream_session_manager_start/stop and the server_stream_ prefix, note the manager is now a file-static singleton hidden in the .cpp * server-stream: move stream traces to debug level keep the bring-up traces for diagnostics but off the default log: skip drain, draining, drain ended, DELETE evict, attach_pipe, and the router stream resume proxy. * server-stream: align router stream resume proxy trace with upstream the child-side bring-up traces are already SRV_TRC on master, move the router stream resume proxy trace to the same level. * server-stream: move stream_read_status enum to the cpp it is only used by the hidden session and consumer types, so it belongs with them behind the pimpl boundary, not on the public header surface. --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Improvement of the CI to run on all hip-related changes as a follow-up to ggml-org#25373 so breakage is more likely to be caught in future
* cli: move to HTTP-based implementation * wip * working * remote server ok * cli support router mode Co-authored-by: Piotr Wilkin <ilintar@gmail.com> * case: router with only one model * Apply suggestions from code review Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com> * remove outdated comment * use destructor instead * add ftype * cli-view --> cli-ui * pimpl * no more json in header * nits fixes * also show model aliases --------- Co-authored-by: Piotr Wilkin <ilintar@gmail.com> Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
…_ID and FLASH_ATTN_EXT (ggml-org#25425) * hex-fa: refactor kernel param compute to use common layout builder * hmx: add explicit compiler barriers to make hmx funcs more robust * hex-vtcm: more generic vtcm layout builder for mm and flash-attn kernels * hex-hmx: unroll inner kernels * hex-hmx: use inline asm instead of intrinsics to avoid compiler issues * hex-hmx: define inline asm macros and simplify code * hex-hmx: replace leftover intrinsics * hmx-fa: minor cleanup for hmx asm * hmx-mm: move per-task stucts out of the kernels header * hmx-mm: simplify core_dot_chunk * hmx-mm: simplify inner loops that call hmx instructions * hmx-mm: proper instrumentation for activation prep work for dma pipelined version * hmx-mm: update a-prep loop for better prefetch * hex-vtcm: improved vtcm layout alloc for mm to support overlapping areas * hmx-mm: reduce the number of act fetch tows to 4 for now, going larger doesnt help here * hex-hmx: always use hmx-queue in all modes * hmx-mm: update comments and minor formatting * hmx-mm: further improve synchro fallback path to prefetch the weights earlier * hex-fa: further pipeline improvements (earlier prefetch) * hmx-mm: cleanup dma pipelines to use dst cached in the queue * hmx-fa: minor cleanup and opts for fa dma pipelines * hmx-fa: optimize q-prep stage with dma and unrolling * hmx-fa: use o_tile size from layout instead of computing it * hmx-mm: cleanup types and size handling * hmx-mm: replace divs with fastdiv in qprep loops * hmx-fa: minor update/formatting to q_tile handling * hmx-fa: cleanup the layout to avoid overpadding * hmx-fa: simplified and improved cost mode for hmx fa solver that uses vtcm layout funcs * hmx-queue: add support queue wakeup and make suspend async to avoid hmx-lock latency * hex-hmx: move queue wakeup / suspend to the op-batch level * hex-threads: add hybrid polling to workpool * hex-mm: fix trailing spaces
…xpert tiles) (ggml-org#25433) * opencl: ragged-tile MoE prefill GEMM (skip padded expert tiles) The MoE prefill GEMM groups tokens into TILESIZE_N=32 per-expert tiles; at low tokens-per-expert most tiles are mostly padding. When a tile's upper 16 slots are all padding (router index 0xFFFFFFFF), skip the second dotx16_reduce8 half. Numerically identical (skipped lanes are padding). Applied to all eight *_f32_ns MoE GEMMs; default on, opt out with GGML_OPENCL_MOE_RAGGED_FP16=0. * opencl: quarter-granularity ragged MoE tile-skip (8-col skip-groups) Replace the two half-tile dotx16_reduce8 calls in the 8 *_f32_ns MoE GEMMs with four dotx8_reduce4 (8-column) calls, skipping each empty trailing skip-group independently. Padding is always trailing, so the kernel rounds the valid count up to the skip granularity and skips fully-padding groups. Byte-identical to the non-skipped path. New env GGML_OPENCL_MOE_RAGGED_GRAN={8,16,32} (quarter/half/ off); default quarter. * opencl: move ragged moe env var in cl_init --------- Co-authored-by: Li He <lih@qti.qualcomm.com>
…4362) * vulkan: disable FA mask_opt on GCN to improve performance * reenable mask opt over attention head size 256
… of 128. (ggml-org#25464) * opencl: fix garbled output for Q6_K weights with ne01 % 128 != 0 on Adreno Observed with granite-3.1-3b-a800m-instruct, whose vocab is an odd number. Route Q6_K dense mul_mat with ne01 % 128 != 0 off the noshuffle path: decode (ne1==1) uses the correct flat GEMV and the matching GEMM (ne1>1) falls back to CPU (the flat convert has no verified small-batch GEMM kernel for these shapes). All standard hidden/FFN/vocab dims are multiples of 128 and keep the noshuffle path. * opencl: reserve alignment slack for the SOA subbuffer carve in alloc size set_tensor carves quantized weights into per-component subbuffers (d/q, ql/qh/s/d, ...) whose origins are each rounded up to the device base address alignment. When a component's size is not a multiple of the alignment, the carve extends past ggml_nbytes(tensor) and the last subbuffer overlaps the next tensor in the pool -- e.g. q6_K [1536, 49155]: size_s = 49155*96 ends 32 bytes past a 128-byte boundary, so the d subbuffer ends 96 bytes past the tensor's allocation, and whichever of the two neighboring tensors is uploaded last silently corrupts the other (here: the last vocab rows' block scales). This affects any quant type whose component sizes can be misaligned, on any shape with ne01 not a multiple of the alignment granularity; standard power-of-two dims are unaffected. Implement get_alloc_size for the OpenCL buffer type and reserve the worst-case carve slack (4 aligned gaps; 5 components max, q5_K) for quantized tensors. Costs at most 512 bytes per quantized tensor at the observed 128-byte alignment. * opencl: use lm based q6_k mm when ne1 is not multiple of 128 --------- Co-authored-by: Li He <lih@qti.qualcomm.com>
* hexagon: add VISION RoPE support * hexagon: support RoPE on strided half-dim views for all modes * hex-rope: decouple src0 DMA copy size from row stride * hex-rope: support non-contiguous dst for RoPE * hex-rope: fix dst spad pitch for non-contiguous dst
) * cuda: fix snake fusion type predicate, a and inv_b are F32 The matcher required a->type == x->type while launch_snake reads both as const float *, matching the CPU and Metal contract where a and inv_b stay F32. F16/BF16 chains never fused and fell back to the naive path, and a hypothetical all F16 chain would have read F16 bits as float. Aligns the predicate and the comment with ggml-cpu.c * cuda: reject snake fusion on non-contiguous operands The kernel reads x[idx] and a[c] / inv_b[c] linearly, so a non-contiguous view passing the matcher would silently read wrong data. Mirror the contiguity guard already present in the CPU, Vulkan and Metal matchers.
CUDA is compiled with fast math and AMD/HIP is not — this flag lets AMD use fast math too. We can't use -ffast-math: it implies -ffinite-math-only, which won't compile (ggml uses INFINITY for masking) and produces NaNs. -funsafe-math-optimizations gives the speedup without the NaN problems. Co-authored-by: Mark Caldwell <mark@cloudhands.ai>
* metal : add CONV_2D_DW (depthwise 2D convolution) support * test : add perf cases for CONV_2D_DW * metal : use 3D dispatch for CONV_2D_DW kernel * metal : add channel-tiled CONV_2D_DW kernel for non-contiguous layouts * metal : simplify CONV_2D_DW dispatch and trim comments * metal : merge duplicate CONV_2D_DW pipeline getters * tests : add F16 CONV2D_DW tests * cpu : fix F16 kernel support for CONV_2D_DW * tests : remove commented-out CONV_2D_DW test block --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
…rg#24908) * Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, DeepSeek-V3 style leading-dense and routed/shared experts, and swigluoai activation. Sparse attention is not yet supported (dense fallback); vision tower and MTP heads are dropped. * MiniMax-M3 vision tower (mmproj + clip graph) * Delete m3_vision_ref.py * Update clip.cpp * MSA * Update constants.py * Update minimax.py * Cache creation. Working withotu flash attention * Added flash attention for sparse layers * Decomposed slow cpu OP into GPU + CPU ops. Massive speedup over long ctx * Rewrote indexer op to be cuda native. Modified flash attention to match per group block picking * Implement sparse attention calc out of stock ops. * Fix a cache allocation and cont issue * Fixed -fa auto crash, flagged debug spots * Delete vocab.json * Delete model.safetensors.index.json * Delete generation_config.json * Delete Minimax directory * Handled multi stream case to fall back on Dense Attention * Development scaffolding cleanup. No functional change to the decode or 4-way paths. Full debug harness remains at <8136a9c68ed7a5eb009aa67bba3fda8062f4648f> for reproducing the selection-parity validation. * Remove redundant comment from minimax-m3.cpp * Changed 3 Gelu Ops for vision into Gelu_erf ops * Assert that n_kv is multiple of 128 * Rename MSA index tensors to indexer convention Note: All GGUFs generated before this change will need to be regenerated. * Fix incorrect Assert * Review driven changes (#3) * Remove comment from conversion minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespaces from constants.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Tighten comment in minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * inherit MiniMax-M3 from MiniMax-M2 * drop dead text_config fallbacks * Add indexer writer methods * Reuse LLM_FFN_SWIGLU_OAI_MOE * Remove duplicate indexer setters, add only block_size/local_blocks, follow value naming convention * Fix conversion error /gguf_writer.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update gguf-py/gguf/gguf_writer.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update conversion/minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update conversion/minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespace in src/llama-kv-cache.cpp Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove Whitespace in Update src/llama-model.h Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespace in src/llama-hparams.h Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * remove multimodal code upon maintainer request. Will be made as a separate PR * Whitespace clean in tensor_mapping.py * Log cache size on launch, block ctx shift, support prompt caching Log indexer cache size on launch Disallow ctx shift Support prompt caching * Update minimax-m3.cpp * Optimize implementation, add multi stream support. Fully rewrote minimax-m3.cpp for speed and buffer size gains: Unified the 4-way + decode, 1 FA call per layer instead of 4, with the groups mapped onto ne[3] Custom CPU op now emits block-level mask, expanded on GPU, which causes CPU to GPU transfer to shrinks at prefill Decode: ~25 nodes/layer vs ~50, no per-group concats/conts Unified selection semantics, so both regimes rank bs + local bias (position-anchored local force), which means prefill/decode can no longer disagree on selection can_reuse on the MSA bias input. Graph reuse at decode restored (was rebuilding the full graph every token) In-place mask adds, shrinking compute buffer ~6.8 to ~4.2 GiB at ub2048/62k Multi-stream: MSA now runs with -np N when kv_unified=false. Decode stays batched across streams (still 1 FA call), prefill loops per stream. dense fallback only for --kv-unified + multi-seq Measured effect on expert offload bound setup: decode 6.2(4WAY)–7.15(MSA_decode) -> 7.7~7.8 t/s, flat from 5k to 60k+. prefill around 10% faster. buffer about 20% smaller, multi-user support. * set default cache type to F32 * Fix potential DSA double indexer cache allocation bug, only allocate in-cache k_idx for archs that opt in * remove F16 downcasts in MSA attention, force F32 indexer score accum * Add Minimax eos to llama vocab * Guard edge case where idx cache can become stale after a tail trim * Update llama-kv-cache.h * Update llama-kv-cache.cpp * Update llama-kv-cache.cpp * Update llama-kv-cache.h * Update llama-kv-cache.cpp * Review driven changes * style fix * indexer hparams are required * fix tests * fix lint --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Eric Hartford <eric@quixi.ai>
…g#26121) * ui: detect the conversation import format from file contents iOS resolves every accept entry to a UTI and has none for ".jsonl", so the picker greyed out exported conversations. Drop the accept filter and pick the parser from the file contents: ZIP magic bytes, then a first "session" record for JSONL, otherwise the legacy JSON format. Also remove the unused importConversations() picker and an orphan doc comment, and cover each format with unit tests. * ui: report what a conversation import actually wrote The import summary echoed the selection back, so re-importing conversations already in the database claimed success while nothing was written and only a console warning said otherwise. Return the imported and skipped conversations from the database layer, list the written ones in the summary, and count the rest in a toast. * ui: name the literals of the JSONL conversation format Introduce SessionRecordType and SESSION_HARNESS, and reuse the existing NEWLINE constant, so the record format lives in one place. This also covers the writer side, which predates the import path under review and carried the same literals: an enum stated by the reader alone lets the two sides drift. Values are unchanged, so an export stays byte identical.
…g#26144) * Keep Minimax's indexer tensors at F32 for speed and accuracy * name -> new_name
…g#26006) The in-conversation system-message edit textarea had a fixed min-height and no auto-resize, so long messages were crammed to 2 lines. Reused existing autoResizeTextarea helper on input and when the editor opens, and added max-height to cap growth.
* Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, DeepSeek-V3 style leading-dense and routed/shared experts, and swigluoai activation. Sparse attention is not yet supported (dense fallback); vision tower and MTP heads are dropped. * MiniMax-M3 vision tower (mmproj + clip graph) * Delete m3_vision_ref.py * Update clip.cpp * MSA * Update constants.py * Update minimax.py * Cache creation. Working withotu flash attention * Added flash attention for sparse layers * Decomposed slow cpu OP into GPU + CPU ops. Massive speedup over long ctx * Rewrote indexer op to be cuda native. Modified flash attention to match per group block picking * Implement sparse attention calc out of stock ops. * Fix a cache allocation and cont issue * Fixed -fa auto crash, flagged debug spots * Delete vocab.json * Delete model.safetensors.index.json * Delete generation_config.json * Delete Minimax directory * Handled multi stream case to fall back on Dense Attention * Development scaffolding cleanup. No functional change to the decode or 4-way paths. Full debug harness remains at <8136a9c68ed7a5eb009aa67bba3fda8062f4648f> for reproducing the selection-parity validation. * Remove redundant comment from minimax-m3.cpp * Changed 3 Gelu Ops for vision into Gelu_erf ops * Assert that n_kv is multiple of 128 * Rename MSA index tensors to indexer convention Note: All GGUFs generated before this change will need to be regenerated. * Fix incorrect Assert * Review driven changes (#3) * Remove comment from conversion minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespaces from constants.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Tighten comment in minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * inherit MiniMax-M3 from MiniMax-M2 * drop dead text_config fallbacks * Add indexer writer methods * Reuse LLM_FFN_SWIGLU_OAI_MOE * Remove duplicate indexer setters, add only block_size/local_blocks, follow value naming convention * Fix conversion error /gguf_writer.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update gguf-py/gguf/gguf_writer.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update conversion/minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update conversion/minimax.py Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespace in src/llama-kv-cache.cpp Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove Whitespace in Update src/llama-model.h Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Remove whitespace in src/llama-hparams.h Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> * Update minimax_m3.cpp Rewrite code comment based on feedback and to better reflect the actual architecture, and reuse existing build_vit * Rename minimax_m3.cpp to minimax-m3.cpp * Update CMakeLists.txt * Remove debug code from clip.cpp * Update clip.cpp * Update comments in tools/mtmd/models/minimax-m3.cpp * Permute Q/K at conversion, drop precomputed sin/cos * Log cache size on launch, block ctx shift, support prompt caching Log indexer cache size on launch Disallow ctx shift Support prompt caching * Update minimax-m3.cpp * Optimize implementation, add multi stream support. Fully rewrote minimax-m3.cpp for speed and buffer size gains: Unified the 4-way + decode, 1 FA call per layer instead of 4, with the groups mapped onto ne[3] Custom CPU op now emits block-level mask, expanded on GPU, which causes CPU to GPU transfer to shrinks at prefill Decode: ~25 nodes/layer vs ~50, no per-group concats/conts Unified selection semantics, so both regimes rank bs + local bias (position-anchored local force), which means prefill/decode can no longer disagree on selection can_reuse on the MSA bias input. Graph reuse at decode restored (was rebuilding the full graph every token) In-place mask adds, shrinking compute buffer ~6.8 to ~4.2 GiB at ub2048/62k Multi-stream: MSA now runs with -np N when kv_unified=false. Decode stays batched across streams (still 1 FA call), prefill loops per stream. dense fallback only for --kv-unified + multi-seq Measured effect on expert offload bound setup: decode 6.2(4WAY)–7.15(MSA_decode) -> 7.7~7.8 t/s, flat from 5k to 60k+. prefill around 10% faster. buffer about 20% smaller, multi-user support. * set default cache type to F32 * Fix potential DSA double indexer cache allocation bug, only allocate in-cache k_idx for archs that opt in * remove F16 downcasts in MSA attention, force F32 indexer score accum * Add Minimax eos to llama vocab * Guard edge case where idx cache can become stale after a tail trim * Update llama-kv-cache.h * Update llama-kv-cache.cpp * Update llama-kv-cache.cpp * Update llama-kv-cache.h * Change resize Pad to none, resize alg to Bicubic Pillow * Review driven changes * Update llama-kv-cache.cpp * rm unrotated pos_t * fused rope w + pad * rename merge --> merger for consistency * add review skill for mtmd * graph should use hparams n_merge * fix lint --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Update sandbox.ts * Update sandbox.ts * Update sandbox.ts * Update sandbox.ts * Revise nerdamer description in sandbox constants Updated NERDAMER_DESCRIPTION to clarify usage and warnings.
…ml-org#26137) * server + ui: refactor resumable stream routes to query string conv_id The conversation id can embed a model name containing slashes (ggml-org/...) in router mode, which the decoded path splits before the :conv_id param is captured, so stop and resume never matched the session. Move the id to the conv_id query string on the public routes and on the internal router -> child hop, where slashes survive encoding. Handlers are unchanged since query and path params land in the same map. Add a regression test with a slashed model name. * server: move stream route docs to server-stream.h Address review: ngxson wants the main server.cpp registration code kept clean and simple, with route-level explanations living in the header. Move the query string rationale and the lookup ownership note next to the handler declarations in server-stream.h, and shorten the wiring comment to a pointer. * server: cancel a pending request when its stream is stopped during model load The conversation was registered in the conv map only after the blocking autoload wait, so a stop issued while the model loaded found nothing to cancel and the request went on to generate an orphan once the load ended. Register the conversation before the wait and give the entry a ticket: a stop erases the entry, and the parked request checks its ticket after the wait and aborts with 400 instead of starting. A newer request on the same conversation replaces the entry, so only the stopped request is cancelled. Add a regression test that stops during the load window. * server + ui: resume a stream after a page reload during model load A pending request died with the client socket when the page was reloaded while its model was loading, so no session ever existed and the conversation had nothing to recover. A session request that waited for a load now detaches from the client socket and reaches the child regardless, the session buffer receives the generation, and the resume route answers 503 while the owner is loading so the client retries instead of dropping its state. The WebUI persists the pending stream at send time, quietly polls on 503, and attaches once the session exists. Add a regression test that drops the client during the load window. * ui: show the model load progress again after a page refresh The resume wait was invisible, so a conversation refreshed while its model was loading showed nothing until the first byte. On a 503 from the resume probe, mark the conversation as loading again so the assistant row persisted at send time renders the processing info, and target the model frozen in the persisted stream state for the progress, since the row has no model yet and the dropdown may not be restored. * fix CI * fix CI bis
* arg: add `-lm mlock` where it mlocks but doesnt mmap Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: rm unwanted docs changes Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: revert auto-formatting Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * bench: fix automated review point 3 Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: revert the meaning of --mlock to non-mmap'ed mlock Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: update docs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: remove extra changes from `llama-gen-docs` Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
* docs: add exception about weight folding * add example
…ml-org#26165) * common: fix explicit -md precedence over draft sidecar resolution Follow-up of ggml-org#25955, an explicit --model-draft file given with -hfd was silently overridden by the sidecar resolution of the draft repo, and its path was never resolved to a local file. An explicit draft file selection now disables the sidecar resolution, so the manual CLI configuration wins over the automatic one. * common: apply the -hfd tag to the sidecar resolution The sidecar selection was anchored on the primary of the draft plan, so a tag without a matching full model aborted the whole plan, and the sidecar quant silently followed the default model pick. The tag now anchors the sidecar directly: exact tag match first, then closest quant to the tag, and a requested sidecar resolves even when no full model matches the tag. A wired draft sidecar also counts as an explicit draft, so the main plan no longer downloads a second one. * common: promote speculative load logs from trace to info Show the loaded draft model and the MTP draft context at the default verbosity, for consistency with the mmproj and primary logs. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
…25832) * ggml : adjust logic for offloading ops to weight's backend * llama : dsv4 graph fixes
* support nanbeige4.2 model * fix * fix flake8 Lint check * fix loop bound check and drop redundant head_dim --------- Co-authored-by: root <lizongqiang@kanzhun.com>
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
* gguf converter for mimo audio * fix conv * cpp impl * nits * nits 2
* contrib : add guideline about the "merge ready" label * cont : add ref [no ci]
* metal fwht wip * shape guard and formatting * formatting * Formatting and typos Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com> * fix narrowing issue Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com> * cont : minor style --------- Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
TRIAGE (automated, advisory) Class: harvest/rebase — narrow single-feature branch (MLA LoRA conversion only), same rebase lineage as #168. Acting agent: crystal-mom (triage subagent) |
Collaborator
Author
|
HAI gate: HOLD. Current head c246830 is conflicting and presents an 882-file aggregate diff for a nominally narrow MLA LoRA change. Restack only the feature delta onto current ht, demonstrate a clean merge base, and rerun focused conversion tests before rereview. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
UPSTREAM-CANDIDATE (clean branch; upstream submission gated at dispatcher desk)
Harvested 2026-09-03 from the gem worker/reviewer checkouts (work dated 2026-08-15) under the Pascal optimization-team charter. Branch:
gems/diamond/upstream-candidate-mla-lora.Commits:
-ffast-mathon HIP ggml-org/llama.cpp#25495)Triage pending; no merge before verdict.
Acting agent: crystal-mom