diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index ce4e1197b..1e4a0870f 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -1234,7 +1234,7 @@ qwen3.5-fp8-b200-sglang-agentic-mtp: - { tp: 4, ep: 1, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [16, 18, 20, 22, 24, 28, 32] } qwen3.5-fp4-b200-sglang: - image: lmsysorg/sglang:v0.5.14-cu130 + image: lmsysorg/sglang:v0.5.19-cu130 model: nvidia/Qwen3.5-397B-A17B-NVFP4-V2 model-prefix: qwen3.5 runner: cluster:b200-nscale diff --git a/perf-changelog.yaml b/perf-changelog.yaml index e707d6070..278d10250 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -7108,3 +7108,10 @@ 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 + +- config-keys: + - qwen3.5-fp4-b200-sglang + description: + - "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