Skip to content

[AMD] Tune MiniMax-M3 MXFP8 MI300X vLLM: async scheduling + big-prefill, fix conc256 EP8→EP1#1951

Open
ZhengGong-amd wants to merge 8 commits into
mainfrom
minimaxm3-mi300x-tuning
Open

[AMD] Tune MiniMax-M3 MXFP8 MI300X vLLM: async scheduling + big-prefill, fix conc256 EP8→EP1#1951
ZhengGong-amd wants to merge 8 commits into
mainfrom
minimaxm3-mi300x-tuning