Skip to content

[NV] minimaxm2.5 fp8 b300 vllm update #1106

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
hshrivastava-droid merged 5 commits into from
Apr 21, 2026
Merged

[NV] minimaxm2.5 fp8 b300 vllm update #1106

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
8babce4
update vllm
hshrivastava-droid Apr 21, 2026
b256571
update Pr number
hshrivastava-droid Apr 21, 2026
08fa198
Merge branch 'main' into minimaxm2.5-fp8-b300-vllm-v2
Ankur-singh Apr 21, 2026
7c0de34
Merge branch 'main' into minimaxm2.5-fp8-b300-vllm-v2
hshrivastava-droid Apr 21, 2026
54bf90e
update conc
hshrivastava-droid Apr 21, 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
11 changes: 6 additions & 5 deletions .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3538,15 +3538,16 @@ minimaxm2.5-fp8-b300-vllm:
- isl: 1024
osl: 1024
search-space:
- { tp: 2, conc-start: 4, conc-end: 512 }
- { tp: 4, conc-start: 4, conc-end: 512 }
- { tp: 2, ep: 2, conc-start: 512, conc-end: 512 }
- { tp: 4, conc-start: 4, conc-end: 128 }
- { tp: 4, ep: 4, conc-start: 256, conc-end: 512 }
- { tp: 2, ep: 2, conc-start: 512, conc-end: 1024 }
- { tp: 2, ep: 2, dp-attn: true, conc-start: 1024, conc-end: 1024 }
- isl: 8192
osl: 1024
search-space:
- { tp: 2, conc-start: 4, conc-end: 512 }
- { tp: 4, conc-start: 4, conc-end: 512 }
- { tp: 1, conc-start: 4, conc-end: 16 }
- { tp: 2, conc-start: 64, conc-end: 256 }
- { tp: 4, conc-start: 4, conc-end: 8 }

minimaxm2.5-fp4-b200-vllm:
image: vllm/vllm-openai:v0.19.0-cu130
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/single_node/minimaxm2.5_fp8_b300.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ hf download "$MODEL"
SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}

export VLLM_FLASHINFER_ALLREDUCE_BACKEND=mnnvl
export VLLM_FLOAT32_MATMUL_PRECISION=high
Copy link
Copy Markdown
Contributor

@functionstackx functionstackx Apr 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can u update the vllm recipe?


if [ "$EP_SIZE" -gt 1 ]; then
EP=" --enable-expert-parallel"
Expand Down
6 changes: 6 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1678,3 +1678,9 @@
- "Add H200 multinode evals-only runs"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1094
evals-only: true

- config-keys:
- minimaxm2.5-fp8-b300-vllm
description:
- "Add VLLM_FLOAT32_MATMUL_PRECISION=high, remove VLLM_FLASHINFER_ALLREDUCE_BACKEND=mnnvl"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1106
Loading