From a4d6073e0651eb63d09bdc997ed3392a17a6d6b1 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 04:14:26 +0000 Subject: [PATCH 1/2] chore(dsv41flash): update H200 SGLang AgentX DSpark image to nightly-dev-cu13-20261028-586355a8 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..a8395f7c9a 100644 --- a/inferencex-e2e/configs/nvidia-master.yaml +++ b/inferencex-e2e/configs/nvidia-master.yaml @@ -9097,7 +9097,7 @@ dsv41flash-fp4-h200-vllm-agentic-dspark: # Match published vLLM TP4/EP1 and TP8/EP1 using dsv4 attention and the nightly's # native MXFP4 x BF16 Marlin MoE runner. dsv41flash-fp4-h200-sglang-agentic-dspark: - image: lmsysorg/sglang:nightly-dev-cu13-20261013-7224fce1 + image: lmsysorg/sglang:nightly-dev-cu13-20261028-586355a8@sha256:b4f09a2ccbcfcc262d49600c3cd7f8581a793ea7d104947257b6a95500953b90 model: deepseek-ai/DeepSeek-V4.1-Flash model-prefix: dsv41flash runner: cluster:h200-dgxc From 767303780e5b209848527035ae82d037639f7ce0 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 06:03:42 +0000 Subject: [PATCH 2/2] chore(dsv41flash): add perf-changelog entry for H200 SGLang AgentX DSpark image update 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 907bd21213..2958c4deb5 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11489,3 +11489,10 @@ - "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: + - dsv41flash-fp4-h200-sglang-agentic-dspark + scenario-type: [agentic-coding] + description: + - "Update the H200 SGLang image from nightly-dev-cu13-20261013-7224fce1 to nightly-dev-cu13-20261028-586355a8." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4597