[Bugfix] Reduce _npu_flash_attention mask to 128x128 for memory savings#1100
Closed
ApsarasX wants to merge 1 commit into
Closed
[Bugfix] Reduce _npu_flash_attention mask to 128x128 for memory savings#1100ApsarasX wants to merge 1 commit into
ApsarasX wants to merge 1 commit into
