From ebf645526a9178e1131a99593071e6fa01d04107 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Mon, 7 Sep 2026 20:46:44 -0400 Subject: [PATCH] [Klaud Cold] Update minimaxm3-fp8-h200-vllm-agentic-mtp vLLM image to nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 Co-Authored-By: Claude Fable 5.1 --- configs/nvidia-master.yaml | 2 +- perf-changelog.yaml | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index 0a6c86df6d..ece824f462 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -7529,7 +7529,7 @@ minimaxm3-fp8-h100-vllm-agentic-mtp: - { tp: 8, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: mooncake, version: "0.3.11.post1" }, conc-list: [6, 8] } minimaxm3-fp8-h200-vllm-agentic-mtp: - image: vllm/vllm-openai:v0.27.1 + image: vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 model: MiniMaxAI/MiniMax-M3-MXFP8 model-prefix: minimaxm3 runner: cluster:h200-dgxc diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 6b249ea15e..38be06d49c 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6921,3 +6921,11 @@ - "Pick up the latest automatic ROCm DeepSeek-V4 optimizations, including fused mHC post/pre plus RMSNorm, gfx950 C4A top-k dispatch, fused C4 compressor GEMMs, fused SWA q/kv RMSNorm plus q FP8 quantization, and medium-batch cooperative top-k tuning." - "Keep the existing VLLM_ROCM_USE_AITER=1, VLLM_ROCM_USE_AITER_MOE=1, and --moe-backend aiter settings, and explicitly add VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=1 plus VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4 to both STP and MTP paths. The current checkpoint's shared-expert path does not satisfy the latest vLLM fusion conditions, so that fusion flag self-disables while preserving recipe parity." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2792 + +- config-keys: + - minimaxm3-fp8-h200-vllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Update vLLM image from vllm/vllm-openai:v0.27.1 (v0.27.1 release) to vllm/vllm-openai:nightly-d9105ea8001e0a6d77a96327d17515bb5791fb36 (2026-09-07 upstream nightly, digest sha256:254eebf919e8b7b0d530d97fccc606c36f380ff6724d64bc190951bec1aee838, tag commit vllm-project/vllm@d9105ea8; Docker Hub last pushed 2026-09-07T06:16:01Z), the same tag the B200 MiniMax-M3 AgentX recipe moved to in #2860 and the ROCm counterpart of the MI325X/MI300X bumps in #2872/#2873. benchmarks/single_node/agentic/minimaxm3_fp8_h200_mtp.sh is unchanged: TRITON_ATTN attention, fp8 KV, EAGLE3 with the Inferact MiniMax-M3 EAGLE3-GQA draft pinned to FLASH_ATTN and the committed golden synthetic acceptance length 2.78, Mooncake 0.3.11.post1 DRAM offload on the host-tier arm; the resident TP8 c1/c2/c4/c6/c8/c10 and Mooncake DRAM offload c12/c14 grid is unchanged." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2875