diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 59f655945..5785c632b 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -314,7 +314,7 @@ qwen3.5-fp8-mi355x-sglang-disagg: qwen3.5-fp4-mi355x-sglang: image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730 - model: amd/Qwen3.5-397B-A17B-MXFP4 + model: amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2 model-prefix: qwen3.5 runner: mi355x precision: fp4 @@ -346,7 +346,7 @@ qwen3.5-fp4-mi355x-atom: qwen3.5-fp4-mi355x-sglang-mtp: image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730 - model: amd/Qwen3.5-397B-A17B-MXFP4 + model: amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2 model-prefix: qwen3.5 runner: mi355x precision: fp4 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 93b6a7c1b..898ae2e21 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6251,3 +6251,12 @@ description: - "Refresh with lower stream interval to collect correct client metrics" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2686 + +- config-keys: + - qwen3.5-fp4-mi355x-sglang + - qwen3.5-fp4-mi355x-sglang-mtp + scenario-type: + - fixed-seq-len + description: + - "Switch the served checkpoint from amd/Qwen3.5-397B-A17B-MXFP4 to amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2 on both arms." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2695