[feat] support fa3 backend for pd disaggregated (#2695)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled

* support fa3 backend run in pd disaggregated

* support fa3 backend run in pd disaggregated

* support fa3 backend run in pd disaggregated

* support fa3 backend run in pd disaggregated

* delete use_fast_ffn
This commit is contained in:
Yuanle Liu
2025-07-03 22:33:27 +08:00
committed by GitHub
parent 00863c43fd
commit 240bdac2a4
26 changed files with 455 additions and 139 deletions

View File

@@ -24,6 +24,7 @@ class _Backend(enum.Enum):
NATIVE_ATTN = enum.auto()
APPEND_ATTN = enum.auto()
MLA_ATTN = enum.auto()
FLASH_ATTN = enum.auto()
class Platform: