Skip to content

H200 MINIMAX vLLM extend configs #869

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

Open
hshrivastava-droid wants to merge 12 commits into
base: main
Choose a base branch
from
+17 −4
Open

H200 MINIMAX vLLM extend configs #869

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
45ddaf0
extend configs
hshrivastava-droid Mar 5, 2026
53f7cc3
perf change
hshrivastava-droid Mar 5, 2026
c035ae5
remove tp4
hshrivastava-droid Mar 5, 2026
4db963a
enable ep
hshrivastava-droid Mar 5, 2026
eb48394
conc increase
hshrivastava-droid Mar 6, 2026
1fcdea2
fix ep condition
hshrivastava-droid Mar 6, 2026
e425178
update: high conc
hshrivastava-droid Mar 6, 2026
b2a8e4d
Merge remote-tracking branch 'origin/main' into nv/h200-minimax
hshrivastava-droid Mar 6, 2026
80e70fb
Merge branch 'main' into nv/h200-minimax
hshrivastava-droid Mar 7, 2026
82f093c
Merge branch 'main' into nv/h200-minimax
hshrivastava-droid Mar 9, 2026
dd98bae
Merge branch 'main' into nv/h200-minimax
ankursingh-nv Mar 9, 2026
d31e3ae
Merge branch 'main' into nv/h200-minimax
hshrivastava-droid Mar 9, 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
6 changes: 3 additions & 3 deletions .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3428,15 +3428,15 @@ minimaxm2.5-fp8-h200-vllm:
- isl: 1024
osl: 1024
search-space:
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 128 }
- isl: 1024
osl: 8192
search-space:
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 128 }
- isl: 8192
osl: 1024
search-space:
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 128 }

dsr1-fp4-gb200-dynamo-trt:
image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.8.1.post2
Expand Down
8 changes: 8 additions & 0 deletions benchmarks/single_node/minimaxm2.5_fp8_h200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ source "$(dirname "$0")/../benchmark_lib.sh"
check_env_vars \
MODEL \
TP \
EP_SIZE \
CONC \
ISL \
OSL \
Expand All @@ -21,9 +22,16 @@ hf download "$MODEL"
SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}

if [ "$EP_SIZE" -ge 1 ]; then
EP=" --enable-expert-parallel"
else
EP=" "
fi

set -x
vllm serve $MODEL --port $PORT \
--tensor-parallel-size=$TP \
$EP \
--gpu-memory-utilization 0.95 \
--max-model-len $MAX_MODEL_LEN \
--disable-log-requests \
Expand Down
7 changes: 6 additions & 1 deletion perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -931,4 +931,9 @@
- "Switch to --attention-backend ROCM_AITER_UNIFIED_ATTN and add fuse_rope_kvcache compilation pass"
- "Remove deprecated VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION/VLLM_ROCM_USE_AITER_MHA env vars and compilation-config cudagraph_mode"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/867


- config-keys:
- minimaxm2.5-fp8-h200-vllm
description:
- "Extend MiniMax M2.5 FP8 single-node config for H200 with vLLM v0.16.0 (TP8)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/869