diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index f456844e9..ce4e1197b 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -6427,7 +6427,7 @@ qwen3.5-fp8-h100-sglang: - { tp: 8, ep: 8, conc-start: 16, conc-end: 256 } qwen3.5-fp8-h100-sglang-mtp: - image: lmsysorg/sglang:v0.5.14-cu130 + image: lmsysorg/sglang:v0.5.19-cu130 model: Qwen/Qwen3.5-397B-A17B-FP8 model-prefix: qwen3.5 runner: h100 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index f9ab8c736..e707d6070 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -7102,3 +7102,9 @@ - "Update SGLang image from lmsysorg/sglang:v0.5.14-cu130 to lmsysorg/sglang:v0.5.19-cu130 (digest sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9)." - "Model nvidia/Qwen3.5-397B-A17B-NVFP4-V2, TP4/EP1 and TP2/EP2 topologies, the 8k/1k workload, EAGLE (3,1,4) MTP settings and the launch script are unchanged." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2950 + +- config-keys: + - qwen3.5-fp8-h100-sglang-mtp + description: + - "Update SGLang image from lmsysorg/sglang:v0.5.14-cu130 to lmsysorg/sglang:v0.5.19-cu130 (digest sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9); recipe script, TP8/EP8 topology and EAGLE/MTP settings unchanged." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2952