diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 59c333c14e..677eb747a9 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -1,5 +1,5 @@ dsr1-fp4-b200-sglang: - image: lmsysorg/sglang:v0.5.5-cu129-amd64 + image: lmsysorg/sglang:v0.5.6-cu129-amd64 model: nvidia/DeepSeek-R1-0528-FP4-V2 model-prefix: dsr1 runner: b200 @@ -75,7 +75,7 @@ dsr1-fp4-b200-trt: - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 256 } dsr1-fp8-b200-sglang: - image: lmsysorg/sglang:v0.5.5-cu129-amd64 + image: lmsysorg/sglang:v0.5.6-cu129-amd64 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: b200 @@ -124,7 +124,7 @@ dsr1-fp8-b200-trt: - { tp: 8, ep: 8, conc-start: 4, conc-end: 64 } dsr1-fp8-h200-sglang: - image: lmsysorg/sglang:v0.5.5-cu129-amd64 + image: lmsysorg/sglang:v0.5.6-cu129-amd64 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: h200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 4361866296..62b230ba67 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -116,3 +116,11 @@ description: - "Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.6.post2" pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/369 + +- config-keys: + - dsr1-fp4-b200-sglang + - dsr1-fp8-b200-sglang + - dsr1-fp8-h200-sglang + description: + - "Update NVIDIA DeepSeek sglang Docker image from v0.5.5 to v0.5.6" + pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/276