Skip to content

[Bugfix] Reduce _npu_flash_attention mask to 128x128 for memory savings

df4cee4
Select commit
Loading
Failed to load commit list.
Closed

[Bugfix] Reduce _npu_flash_attention mask to 128x128 for memory savings #1100

[Bugfix] Reduce _npu_flash_attention mask to 128x128 for memory savings
df4cee4
Select commit
Loading
Failed to load commit list.