From 39a49e16b062cf84f04009d1c3e009a18cdc8204 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 12 May 2026 21:30:20 +0000 Subject: [PATCH] $Update qwen3.5-fp4-b300-sglang SGLang image to v0.5.11-cu130\n\nRef #1154\n\nCo-authored-by: Klaud Cold --- .github/configs/nvidia-master.yaml | 2 +- perf-changelog.yaml | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index f1cec3c52e..60b13a6537 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -2354,7 +2354,7 @@ qwen3.5-fp8-b300-sglang: - { tp: 4, ep: 1, conc-start: 4, conc-end: 256 } qwen3.5-fp4-b300-sglang: - image: lmsysorg/sglang:v0.5.10.post1-cu130 + image: lmsysorg/sglang:v0.5.11-cu130 model: nvidia/Qwen3.5-397B-A17B-NVFP4 model-prefix: qwen3.5 runner: b300 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index ac8269ef24..abfcbe996a 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2343,3 +2343,9 @@ description: - "Add Qwen3.5-397B-A17B FP8 MI355X ATOM benchmark configs with and without MTP" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1310 + +- config-keys: + - qwen3.5-fp4-b300-sglang + description: + - "Update SGLang image from v0.5.10.post1-cu130 to v0.5.11-cu130" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX