From 37d861df4e4bf102b1f53d1402daf36bf7449e0e Mon Sep 17 00:00:00 2001 From: Xin Li Date: Sun, 9 Aug 2026 01:34:57 -0400 Subject: [PATCH 1/2] minimaxm3 fp4 b200 agentic mtp: set --long-prefill-token-threshold 512 --- benchmarks/single_node/agentic/minimaxm3_fp4_b200_mtp.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/benchmarks/single_node/agentic/minimaxm3_fp4_b200_mtp.sh b/benchmarks/single_node/agentic/minimaxm3_fp4_b200_mtp.sh index be705c0c2..23a2c1010 100755 --- a/benchmarks/single_node/agentic/minimaxm3_fp4_b200_mtp.sh +++ b/benchmarks/single_node/agentic/minimaxm3_fp4_b200_mtp.sh @@ -194,6 +194,7 @@ VLLM_CMD=( --max-cudagraph-capture-size 512 --max-num-batched-tokens 16384 --stream-interval 20 + --long-prefill-token-threshold 512 \ --trust-remote-code --speculative-config "$SPEC_CONFIG" "${OFFLOAD_ARGS[@]}" From 8d81fc7705cb66033ca2afc8fc5468ef1853886f Mon Sep 17 00:00:00 2001 From: Xin Li Date: Sun, 9 Aug 2026 01:50:54 -0400 Subject: [PATCH 2/2] fix perf-changelog --- perf-changelog.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 90953bc2d..578a2c523 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -5688,3 +5688,9 @@ - "Use the official lmsysorg/sglang:v0.5.16-rocm720-mi30x image, enable SGLang prompt-cache reporting, and pass the backend Prometheus metrics endpoint explicitly to AIPerf" - "Allow up to 30 minutes for healthy AgentX responses admitted near the end of the measurement window to drain before AIPerf finalizes profile metric coverage" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2528 + +- config-keys: + - minimaxm3-fp4-b200-vllm-agentic-mtp + description: + - "Set --long-prefill-token-threshold 512 for MiniMax M3 NVFP4 b200 AgentX MTP" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2538