From 8a2db717cdcc42e03f962de713e47051c244c588 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 27 Oct 2026 00:24:13 +0000 Subject: [PATCH 1/2] chore(musespark): bump GB300 Dynamo-SGLang AgentX DFlash image to nightly-dev-20261026-8252e3af 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 803a34c839..60defbebc7 100644 --- a/inferencex-e2e/configs/nvidia-master.yaml +++ b/inferencex-e2e/configs/nvidia-master.yaml @@ -9860,7 +9860,7 @@ musespark-fp4-gb300-sglang-agentic-dflash: - { tp: 4, ep: 4, kv-offloading: dram, kv-offload-backend: { name: hicache }, spec-decoding: draft_model, conc-list: [24, 28, 30, 34, 44, 48], srt-recipe: agentic.yaml } musespark-fp4-gb300-dynamo-sglang-agentic-dflash: - image: lmsysorg/sglang:dev-muse-spark-open@sha256:8cfc5a72cb296771f5f8a4a4688cb6d05685610a830cbb616fa4ab0eb7bb2b0a + image: lmsysorg/sglang:nightly-dev-20261026-8252e3af@sha256:b4e4abb9e1dc038f7e14c85805be97e4f74abb46e541bd4edd31401d50a2e593 model: meta-models/Muse-Spark-Open-816B-A42B-NVFP4 model-prefix: musespark runner: cluster:gb300-nv From 212b89552c8a9823e738cd0b74485372a081113e Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 27 Oct 2026 07:49:03 +0000 Subject: [PATCH 2/2] chore(perf-changelog): add Muse-Spark-Open GB300 Dynamo-SGLang image bump entry 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 fd894cc02f..fb1a3518cd 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11413,3 +11413,10 @@ - Restore the MI355X MiniMax-M3 FP4 vLLM AgentX TP2/TP4 grid from run 34609443618 attempt 2 using SRT recipes. Update nightly-2a02f6efe319c885e3ccbcecde402e0028f9ec1e to nightly-df6603f0583375f244d1ac6d36265462b7490392 (2026-10-22, digest sha256:81899892d73777a4ae81e16f39e749169687f29249505eb4c56da83bd097d41c). - Enable upstream MiniMax-M3 monokernel at TP4 with Model Runner V2, AITER MoE, FP8 KV/indexer and block size 128; keep TP2 on ordinary decode. Preserve EAGLE3-GQA with three draft tokens and use automatic golden acceptance for throughput with real verification for evals. pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4418 + +- config-keys: + - musespark-fp4-gb300-dynamo-sglang-agentic-dflash + description: + - "Update the SGLang image from dev-muse-spark-open to nightly-dev-20261026-8252e3af, pinned by digest." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4561 + scenario-type: [agentic-coding]