Skip to content

feat(minimaxm3-fp4-b200-dynamo-vllm): bump vLLM nightly to 5e35a6f4, enable cutlass MSA decode / 更新 minimaxm3-fp4-b200-dynamo-vllm vLLM 镜像至 5e35a6f4，启用 cutlass MSA 解码后端 #2472

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adibarra merged 5 commits into from
Aug 4, 2026
Merged

feat(minimaxm3-fp4-b200-dynamo-vllm): bump vLLM nightly to 5e35a6f4, enable cutlass MSA decode / 更新 minimaxm3-fp4-b200-dynamo-vllm vLLM 镜像至 5e35a6f4，启用 cutlass MSA 解码后端 #2472

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e6ebb16
feat(minimaxm3-fp4-b200-dynamo-vllm): bump vLLM nightly to 5e35a6f4, …
xinli-sw Aug 3, 2026
ceebd48
chore(perf-changelog): add entry for minimaxm3-fp4-b200-dynamo-vllm n…
xinli-sw Aug 3, 2026
37b9824
fix(minimaxm3-fp4-b200-dynamo-vllm): remove cutlass MSA env var from …
xinli-sw Aug 3, 2026
f4bf44a
fix(minimaxm3-fp4-b200-dynamo-vllm): use attention_config field for c…
xinli-sw Aug 3, 2026
f0a80be
chore: resolve append-only changelog conflict
adibarra Aug 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ...multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p1d-dep2-tp4-c1-c16-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-1p1d-fp4-dep2-tp4-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -48,7 +48,7 @@ backend:
trust-remote-code: true
no-enable-prefix-caching: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
kv-cache-dtype: fp8
block-size: 128
gpu-memory-utilization: 0.90
Expand Down
4 changes: 2 additions & 2 deletions ...ks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p2d-dep2-tp4-c64-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-1p2d-fp4-dep2-tp4-c64-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -112,7 +112,7 @@ backend:
served-model-name: nvidia/MiniMax-M3-NVFP4
no-enable-flashinfer-autotune: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
block-size: 128
language-model-only: true
health_check: {max_attempts: 360, interval_seconds: 10}
Expand Down
4 changes: 2 additions & 2 deletions ...s/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p2d-dep2-tp4-c128-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-2p2d-fp4-dep2-tp4-c128-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -112,7 +112,7 @@ backend:
served-model-name: nvidia/MiniMax-M3-NVFP4
no-enable-flashinfer-autotune: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
block-size: 128
language-model-only: true
health_check: {max_attempts: 360, interval_seconds: 10}
Expand Down
4 changes: 2 additions & 2 deletions ...s/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c256-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-3p2d-fp4-dep2-tp4-c256-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -112,7 +112,7 @@ backend:
served-model-name: nvidia/MiniMax-M3-NVFP4
no-enable-flashinfer-autotune: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
block-size: 128
language-model-only: true
health_check: {max_attempts: 360, interval_seconds: 10}
Expand Down
4 changes: 2 additions & 2 deletions ...s/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c512-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-3p2d-fp4-dep2-tp4-c512-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -112,7 +112,7 @@ backend:
served-model-name: nvidia/MiniMax-M3-NVFP4
no-enable-flashinfer-autotune: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
block-size: 128
language-model-only: true
health_check: {max_attempts: 360, interval_seconds: 10}
Expand Down
4 changes: 2 additions & 2 deletions .../multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/4p2d-dep2-tp4-c1024-8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
name: "minimax-m3-vllm-disagg-b200-4p2d-fp4-dep2-tp4-c1024-8k1k"
model:
path: "nvidia/MiniMax-M3-NVFP4"
container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
container: "vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7"
precision: "fp4"
resources:
gpu_type: "b200"
Expand Down Expand Up @@ -112,7 +112,7 @@ backend:
served-model-name: nvidia/MiniMax-M3-NVFP4
no-enable-flashinfer-autotune: true
kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8", "minimax_m3_msa_decode_backend": "cutlass"}'
block-size: 128
language-model-only: true
health_check: {max_attempts: 360, interval_seconds: 10}
Expand Down
2 changes: 1 addition & 1 deletion configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7403,7 +7403,7 @@ qwen3.5-fp8-h100-sglang-agentic:
- { tp: 8, ep: 8, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [12, 14, 16, 20, 24, 28, 32, 42] }

minimaxm3-fp4-b200-dynamo-vllm:
image: vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9
image: vllm/vllm-openai:nightly-5e35a6f4f9bbc217c599692157ca985c894373f7
model: nvidia/MiniMax-M3-NVFP4
model-prefix: minimaxm3
runner: b200-multinode
Expand Down
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5374,3 +5374,10 @@
- "Image: lmsysorg/sglang:v0.5.16-cu130"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2420


- config-keys:
- minimaxm3-fp4-b200-dynamo-vllm
description:
- "Bump vLLM nightly image to nightly-5e35a6f4f9bbc217c599692157ca985c894373f7 (fixed-len MiniMax-M3 fix); update all B200 FP4 8k1k recipe YAML container fields to match"
- "Enable VLLM_MINIMAX_M3_MSA_DECODE_BACKEND=cutlass in prefill and decode environments"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2472