[Refactor] Move fla to third party (#48500)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2026-07-16 19:22:36 +01:00
committed by GitHub
parent 251f7e478e
commit 626c90b2d5
42 changed files with 87 additions and 62 deletions
+3 -1
View File
@@ -286,7 +286,9 @@ class RMSNormGated(CustomOp):
def forward_cuda(
self, x: torch.Tensor, z: torch.Tensor | None = None
) -> torch.Tensor:
from vllm.model_executor.layers.fla.ops.layernorm_guard import rmsnorm_fn
from vllm.third_party.flash_linear_attention.ops.layernorm_guard import (
rmsnorm_fn,
)
return rmsnorm_fn(
x,