Sync with FA v2.6.0 to support soft capping (#13)

d562aa63 · Woosuk Kwon · GitHub · 12375706 · d562aa63
Unverified Commit d562aa63 authored Jul 31, 2024 by Woosuk Kwon Committed by GitHub Jul 31, 2024
Expand all Hide whitespace changes
Inline Side-by-side

Showing with 79 additions and 13 deletions

vllm_flash_attn/flash_attn_interface.py vllm_flash_attn/flash_attn_interface.py +79 -13

No files found.
--- a/vllm_flash_attn/flash_attn_interface.py
+++ b/vllm_flash_attn/flash_attn_interface.py