diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index a167f49270..a388cad95d 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -1524,10 +1524,9 @@ dsr1-fp8-b200-sglang-mtp: # NOTE: At the time of submission, https://cookbook.sglang.io/autoregressive/DeepSeek/DeepSeek-R1 # does not have a B300-specific recipe, so this config reuses the existing DSR1 FP8 - # B200 SGLang MTP recipe as-is until B300-specific tuning is available. Image bumped - # to v0.5.10.post1-cu130 to match the standard B300 SGLang image used by other B300 configs. + # B200 SGLang MTP recipe as-is until B300-specific tuning is available. dsr1-fp8-b300-sglang-mtp: - image: lmsysorg/sglang:v0.5.12-cu130 + image: lmsysorg/sglang:v0.5.15.post1-cu130 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: b300 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 335245a6c3..975c917743 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -5060,3 +5060,9 @@ - "Re-pin VLLM_ROUTER_IMAGE to vllm/vllm-router:nightly-20260716-1fbcde7 (previous nightly-20260629-e667ebb was garbage-collected from Docker Hub)" - "Exclude known-bad nodes mia1-p01-g09,g14 from the disagg node pool" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2301 + +- config-keys: + - dsr1-fp8-b300-sglang-mtp + description: + - "Bump SGLang container image from lmsysorg/sglang:v0.5.12-cu130 to lmsysorg/sglang:v0.5.15.post1-cu130 (https://github.com/sgl-project/sglang/releases/tag/v0.5.15.post1)" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2313