Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200.sh
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
elif [ "$EP_SIZE" -gt 1 ]; then
PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
else
PARALLEL_ARGS="--tensor-parallel-size=$TP"
PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
fi

if [ "${EVAL_ONLY}" = "true" ]; then
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
elif [ "$EP_SIZE" -gt 1 ]; then
PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
else
PARALLEL_ARGS="--tensor-parallel-size=$TP"
PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
fi

# use 3 speculative tokens for all configs for now
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300.sh
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
elif [ "$EP_SIZE" -gt 1 ]; then
PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
else
PARALLEL_ARGS="--tensor-parallel-size=$TP"
PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

thanks for contribution! can u add marlin for blackwell marlin on vllm recipes?

fi

if [ "${EVAL_ONLY}" = "true" ]; then
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
elif [ "$EP_SIZE" -gt 1 ]; then
PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
else
PARALLEL_ARGS="--tensor-parallel-size=$TP"
PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
fi

# use 3 speculative tokens for all configs for now
Expand Down
9 changes: 9 additions & 0 deletions perf-changelog.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3900,3 +3900,12 @@
description:
- "Add Qwen3.5-397B-A17B-NVFP4 B200 single-node TensorRT-LLM benchmark (1k/1k and 8k/1k) with a TP/TEP/DEP parallelism sweep"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1711

- config-keys:
- minimaxm3-fp8-b200-vllm
- minimaxm3-fp8-b300-vllm
- minimaxm3-fp8-b200-vllm-mtp
- minimaxm3-fp8-b300-vllm-mtp
description:
- "Use the Marlin MoE backend for MiniMax-M3 B200/B300 TP-only vLLM configurations by adding --moe-backend marlin when expert parallelism is disabled."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1809