mtmd: Add Vision Support for Minimax-M3 (#25113)
* 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>
This commit is contained in:
timkhronos
co-authored by
Sigbjørn Skjæret
Daniel Han
Xuan Son Nguyen
Sigbjørn Skjæret
Daniel Han
Xuan Son Nguyen
parent
0d47ea7427
commit
3d1c3a8975
@@ -857,6 +857,8 @@ class MODEL_TENSOR(IntEnum):
|
||||
V_MM_UP = auto() # cogvlm
|
||||
V_MM_DOWN = auto() # cogvlm
|
||||
V_MM_GATE = auto() # cogvlm
|
||||
V_MM_MERGER_FC1 = auto() # minimax-m3 (patch-merge MLP)
|
||||
V_MM_MERGER_FC2 = auto() # minimax-m3 (patch-merge MLP)
|
||||
V_TOK_BOI = auto() # cogvlm
|
||||
V_TOK_EOI = auto() # cogvlm
|
||||
V_TOK_IMG_BEGIN = auto() # hunyuanvl
|
||||
@@ -1441,6 +1443,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
|
||||
MODEL_TENSOR.V_MM_UP: "mm.up",
|
||||
MODEL_TENSOR.V_MM_DOWN: "mm.down",
|
||||
MODEL_TENSOR.V_MM_GATE: "mm.gate",
|
||||
MODEL_TENSOR.V_MM_MERGER_FC1: "mm.merger.fc1",
|
||||
MODEL_TENSOR.V_MM_MERGER_FC2: "mm.merger.fc2",
|
||||
MODEL_TENSOR.V_TOK_BOI: "v.boi",
|
||||
MODEL_TENSOR.V_TOK_EOI: "v.eoi",
|
||||
MODEL_TENSOR.V_MM_PRE_NORM: "mm.pre_norm",
|
||||
@@ -1637,6 +1641,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
||||
MODEL_TENSOR.V_RESMPL_QUERY,
|
||||
MODEL_TENSOR.V_TOK_EMBD_IMG_BREAK,
|
||||
MODEL_TENSOR.V_MM_PATCH_MERGER,
|
||||
MODEL_TENSOR.V_MM_MERGER_FC1,
|
||||
MODEL_TENSOR.V_MM_MERGER_FC2,
|
||||
MODEL_TENSOR.V_DS_NORM,
|
||||
MODEL_TENSOR.V_DS_FC1,
|
||||
MODEL_TENSOR.V_DS_FC2,
|
||||
@@ -4771,6 +4777,7 @@ class VisionProjectorType:
|
||||
YOUTUVL = "youtuvl"
|
||||
NEMOTRON_V2_VL = "nemotron_v2_vl"
|
||||
HUNYUANVL = "hunyuanvl"
|
||||
MINIMAXM3 = "minimax_m3"
|
||||
MINICPMV4_6 = "minicpmv4_6"
|
||||
GRANITE_SPEECH = "granite_speech" # audio
|
||||
MIMOVL = "mimovl"
|
||||
|
||||
@@ -1838,6 +1838,14 @@ class TensorNameMap:
|
||||
"visual.downsample", # glm4v
|
||||
),
|
||||
|
||||
MODEL_TENSOR.V_MM_MERGER_FC1: (
|
||||
"patch_merge_mlp.linear_1", # minimax-m3
|
||||
),
|
||||
|
||||
MODEL_TENSOR.V_MM_MERGER_FC2: (
|
||||
"patch_merge_mlp.linear_2", # minimax-m3
|
||||
),
|
||||
|
||||
MODEL_TENSOR.V_DS_NORM: (
|
||||
"model.visual.deepstack_merger_list.{bid}.norm", # deepstack in qwen3vl
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user