diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 811a5c8bb..b19a0390e 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -78,7 +78,7 @@ dsr1-fp8-mi300x-sglang: - { tp: 8, conc-start: 4, conc-end: 64 } dsr1-fp8-mi325x-sglang: - image: lmsysorg/sglang:v0.5.12-rocm700-mi30x + image: lmsysorg/sglang:v0.5.19-rocm700-mi30x model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: mi325x diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 779ca1713..f7af7815b 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -7089,3 +7089,9 @@ - "MTP draft length by concurrency: speculative-num-steps 3 (golden AL 2.49) below conc 256, and 1 (golden AL 1.79) at and above it." - "Trim the search space to TP8 no-offload conc [1, 4, 16], TP8 hicache conc [32, 48], and TP8 DP-attention hicache conc [128, 256]." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2885 + +- config-keys: + - dsr1-fp8-mi325x-sglang + description: + - "Update SGLang image from lmsysorg/sglang:v0.5.12-rocm700-mi30x to lmsysorg/sglang:v0.5.19-rocm700-mi30x" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2949