From e07adbe5e0b3173ab9ecb7d83d57fe6521c199ee Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 12:15:11 +0000 Subject: [PATCH 1/2] chore(minimaxm3): update H200 FP8 vLLM AgentX MTP image to nightly-edad8b03 Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/configs/nvidia-master.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml index dcc8d15576..5c0f908396 100644 --- a/inferencex-e2e/configs/nvidia-master.yaml +++ b/inferencex-e2e/configs/nvidia-master.yaml @@ -5256,7 +5256,7 @@ 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], srt-recipe: agentic.yaml } minimaxm3-fp8-h200-vllm-agentic-mtp: - image: vllm/vllm-openai:nightly-83c078d955cd6e0c63d3b12abe669c8de936a370@sha256:cb12c3016938a4ee98ed176ac833984089460689a0982cff4b5a60bb45b3cded + image: vllm/vllm-openai:nightly-edad8b03c5285a1c12e7e4f83c1af709b319a01b@sha256:2e735ffeef26457f8a3ff44a62ae182870b10af37adc06ecbb08baca152365c6 model: MiniMaxAI/MiniMax-M3-MXFP8 model-prefix: minimaxm3 runner: cluster:h200-dgxc From 99be0a93d1544a7b4bc9fa70c28728dc64d976ab Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 13:46:03 +0000 Subject: [PATCH 2/2] chore(minimaxm3): add perf-changelog entry for H200 FP8 vLLM AgentX MTP image update Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/perf-changelog.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 907bd21213..9dc4dc2607 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11489,3 +11489,11 @@ - "Update the MI355X DeepSeek-V4-Pro-0813 SGLang MoRI disaggregated AgentX serving image from lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261019 to lmsysorg/sglang-rocm:v0.5.22-rocm10-mi35x-20261026, the latest published MI35x ROCm 10 nightly (digest sha256:edabad83728ab04e3eae39f315eb16261eeb64dbdb051112bd22fc88560b60c4)." - "Preserve all eight concurrency points (1, 16, 32, 48, 192, 256, 384, 512), prefill/decode topology, DSpark settings, UMBP offload, MoRI transfer, and benchmark client image. The workload binder supplies the serving image to every selected recipe variant." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4571 + +- config-keys: + - minimaxm3-fp8-h200-vllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Update the H200 MiniMax-M3 FP8 vLLM AgentX MTP image from nightly-83c078d9 to nightly-edad8b03." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4610