diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index bdb6a46029..7d87d4513a 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -3309,7 +3309,7 @@ dsv4-fp4-b300-vllm-mtp: - { tp: 4, ep: 4, dp-attn: true, conc-start: 256, conc-end: 512, spec-decoding: mtp } qwen3.5-fp8-h200-sglang: - image: lmsysorg/sglang:v0.5.12-cu130 + image: lmsysorg/sglang:v0.5.14-cu130 model: Qwen/Qwen3.5-397B-A17B-FP8 model-prefix: qwen3.5 runner: h200 @@ -3328,7 +3328,7 @@ qwen3.5-fp8-h200-sglang: - { tp: 8, ep: 8, conc-start: 4, conc-end: 64 } qwen3.5-fp8-h200-sglang-mtp: - image: lmsysorg/sglang:v0.5.12 + image: lmsysorg/sglang:v0.5.14-cu130 model: Qwen/Qwen3.5-397B-A17B-FP8 model-prefix: qwen3.5 runner: h200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index f13d283d65..320289d243 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -4448,3 +4448,10 @@ - "Employ the AITER MLA attention backend for the DeepSeek-V4 MLA path." - "Switch the MoE backend from triton_unfused to AITER MoE (VLLM_ROCM_USE_AITER_MOE=1 + --moe-backend aiter) for the FP4 experts." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1980 + +- config-keys: + - qwen3.5-fp8-h200-sglang + - qwen3.5-fp8-h200-sglang-mtp + description: + - "Update SGLang image from qwen3.5-fp8-h200-sglang: lmsysorg/sglang:v0.5.12-cu130 / qwen3.5-fp8-h200-sglang-mtp: lmsysorg/sglang:v0.5.12 to lmsysorg/sglang:v0.5.14-cu130" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2061