[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
+2 -2
View File
@@ -10,12 +10,12 @@ import pytest
import torch
import torch.nn.functional as F
from vllm.model_executor.layers.fla.ops.kda import (
from vllm.third_party.flash_linear_attention.ops.kda import (
chunk_kda,
chunk_kda_with_fused_gate,
fused_kda_gate,
)
from vllm.model_executor.layers.fla.ops.l2norm import l2norm_fwd
from vllm.third_party.flash_linear_attention.ops.l2norm import l2norm_fwd
DEVICE = "cuda"