Skip to content

[AMD] Tune MiniMax-M3 MXFP8 MI300X vLLM: async scheduling + big-prefill, fix conc256 EP8→EP1#1950

Closed
ZhengGong-amd wants to merge 5 commits into
SemiAnalysisAI:mainfrom
ZhengGong-amd:minimaxm3-mi300x-combo-tuning
Closed

[AMD] Tune MiniMax-M3 MXFP8 MI300X vLLM: async scheduling + big-prefill, fix conc256 EP8→EP1#1950
ZhengGong-amd wants to merge 5 commits into
SemiAnalysisAI:mainfrom
ZhengGong-amd:minimaxm3-mi300x-combo-tuning