diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index 1e4a0870f..4900fed88 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -1556,7 +1556,7 @@ dsr1-fp8-h200-sglang: - { tp: 8, conc-start: 4, conc-end: 64 } dsr1-fp8-h200-sglang-mtp: - image: lmsysorg/sglang:v0.5.12-cu130 + image: lmsysorg/sglang:v0.5.19-cu130 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: h200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 278d10250..72d7c3537 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -7115,3 +7115,9 @@ - "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/EP1 topologies, the 8k/1k workload and the launch script are unchanged." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2954 + +- config-keys: + - dsr1-fp8-h200-sglang-mtp + description: + - "Update SGLang image from lmsysorg/sglang:v0.5.12-cu130 to lmsysorg/sglang:v0.5.19-cu130 (digest sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9, sglang commit 0bcd822377da7b5718e674eaf9c870d349424dd1); recipe script, TP8/EP1 topology and EAGLE/MTP settings unchanged." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2955