From 82bf53192f19c79508f141ff99f167aac5368542 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 27 Oct 2026 00:23:30 +0000 Subject: [PATCH 1/2] chore(minimaxm31flash): bump GB200 SGLang DSpark image to nightly-cu134-20261026-5ef9901 Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/configs/nvidia-master.yaml | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml index 803a34c839..9554b8dc5c 100644 --- a/inferencex-e2e/configs/nvidia-master.yaml +++ b/inferencex-e2e/configs/nvidia-master.yaml @@ -5746,13 +5746,12 @@ minimaxm3-fp4-gb200-dynamo-vllm-agentic-agg-mtp: ep: 1 dp-attn: false -# MiniMax-M3.1-Flash AgentX on GB200 with SGLang: day-zero image from the SGLang -# cookbook (https://docs.sglang.io/cookbook/autoregressive/MiniMax/MiniMax-M3.1), -# manifest digest verified 2026-10-24. +# MiniMax-M3.1-Flash AgentX on GB200 with SGLang: upstream arm64 CUDA 13.4 +# nightly, which carries the MiniMax-M3.1-Flash support of sgl-project/sglang#45925. # Seven-token DSpark (bundled draft); synthetic acceptance follows # infx/golden_al_distribution/minimaxm31flash_dspark.yaml. minimaxm31flash-fp4-gb200-sglang-agentic-dspark: - image: lmsysorg/sglang:dev-minimax-m31-flash@sha256:614b1509bcb729c653528d448bff9850f8977fcad9d12ba56bd6dbe3d7985e87 + image: lmsysorg/sglang:nightly-cu134-20261026-5ef9901@sha256:64460b432679d4555b6579832454d8b9a21cc8591b2d16b340b94abb59de28e6 model: MiniMaxAI/MiniMax-M3.1-Flash model-prefix: minimaxm31flash runner: cluster:gb200-nv From c06b8328f2260c782fc3cb284021207c2552f94d Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 27 Oct 2026 17:27:44 +0000 Subject: [PATCH 2/2] chore(minimaxm31flash): add perf-changelog entry for GB200 SGLang DSpark image bump Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/perf-changelog.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index bd36ce984f..8a1bee95d6 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11429,3 +11429,10 @@ - "ATOM changes in the new image that matter here: GLM-5.2 mono decode and ATOM_MONO_ENABLE (ROCm/ATOM #2479, #2483, #2535). ATOM_DCP_PREFILL_QREP (#2437) and QREP together with MTP (#2290); the old image turned QREP off whenever MTP was on. DCP prefill fixes with the MTP draft (#2430, #2496, #2506, #2348). MTP verify and draft-graph fixes (#2451, #2367, #2566, #2495). lmcache_offload lookup and save fixes (#2305, #2339, #2547) and the LMCache 0.5.6.dev139+gf22dec28 pin (#2438)." - "Draft data types unchanged: the MTP draft (model.layers.78 of amd/GLM-5.2-MXFP4, which ships all-BF16 including its routed experts) stays BF16 because online_quant_config excludes model.layers.78.* from ptpc_fp8. It uses the FP8 KV cache and FP4 indexer cache like the target. Mono decode covers only target layers 0-77." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4308 + +- config-keys: + - minimaxm31flash-fp4-gb200-sglang-agentic-dspark + description: + - "Update the SGLang image from dev-minimax-m31-flash to nightly-cu134-20261026-5ef9901, pinned by digest." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4559 + scenario-type: [agentic-coding]