diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml index 337047e57..8b6f0d16f 100644 --- a/.github/configs/amd-master.yaml +++ b/.github/configs/amd-master.yaml @@ -73,7 +73,7 @@ dsr1-fp4-mi355x-atom-mtp: - { tp: 8, conc-start: 4, conc-end: 256, spec-decoding: mtp } dsr1-fp8-mi300x-sglang: - image: lmsysorg/sglang:v0.5.9-rocm700-mi30x + image: lmsysorg/sglang-daily:v0.5.9-rocm720-mi30x-20260310 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: mi300x diff --git a/perf-changelog.yaml b/perf-changelog.yaml index c19ddbd1a..9449d4f6d 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -932,3 +932,11 @@ - "Remove deprecated VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION/VLLM_ROCM_USE_AITER_MHA env vars and compilation-config cudagraph_mode" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/867 +- config-keys: + - dsr1-fp8-mi300x-sglang + description: + - "Update MI300X FP8 DSR1 SGLang image from v0.5.8 to lmsysorg/sglang-daily:v0.5.9-rocm720-mi30x-20260310" + - "Include configuration files for three GEMM operations: https://github.com/ROCm/aiter/pull/2024" + - "Improve TPOT by using fp8 bmm in MLA and MI300X for DSR1/V3: https://github.com/sgl-project/sglang/pull/18624" + - "Broaden the optimized paths to all HIP platforms and add tuned FP8 GEMM configs: https://github.com/sgl-project/sglang/pull/18242" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/811