biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] Fix wrong import path of get_flash_attn_version (#15280)

Browse Source 
Signed-off-by: Lehua Ding <lehuading@tencent.com>
This commit is contained in:
Lehua Ding
2025-03-21 18:54:11 +08:00
committed by GitHub
parent 84e00adc8a
commit 91ca929dc7
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/attention/backends/mla/common.py
View File

@@ -195,8 +195,8 @@ from vllm import _custom_ops as ops
from vllm.attention.backends.abstract import (AttentionBackend, AttentionLayer, from vllm.attention.backends.abstract import (AttentionBackend, AttentionLayer,
AttentionMetadata, AttentionMetadata,
MLAAttentionImpl) MLAAttentionImpl)
from vllm.attention.backends.utils import get_flash_attn_version
from vllm.attention.ops.triton_merge_attn_states import merge_attn_states from vllm.attention.ops.triton_merge_attn_states import merge_attn_states
from vllm.fa_utils import get_flash_attn_version
from vllm.logger import init_logger from vllm.logger import init_logger
from vllm.model_executor.layers.linear import (ColumnParallelLinear, from vllm.model_executor.layers.linear import (ColumnParallelLinear,
LinearBase, RowParallelLinear, LinearBase, RowParallelLinear,