Skip to content

minimaxm2.5-fp8-h200-vllm: switch 8k/1k attention backend to FLASH_ATTN#1667

Closed
RohitNagraj wants to merge 2 commits into
SemiAnalysisAI:mainfrom
RohitNagraj:minimax-m25-h200-vllm-8k1k-fa3
Closed

minimaxm2.5-fp8-h200-vllm: switch 8k/1k attention backend to FLASH_ATTN#1667
RohitNagraj wants to merge 2 commits into
SemiAnalysisAI:mainfrom
RohitNagraj:minimax-m25-h200-vllm-8k1k-fa3

Commits