We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 84e00ad commit 91ca929Copy full SHA for 91ca929
vllm/v1/attention/backends/mla/common.py
@@ -195,8 +195,8 @@
195
from vllm.attention.backends.abstract import (AttentionBackend, AttentionLayer,
196
AttentionMetadata,
197
MLAAttentionImpl)
198
-from vllm.attention.backends.utils import get_flash_attn_version
199
from vllm.attention.ops.triton_merge_attn_states import merge_attn_states
+from vllm.fa_utils import get_flash_attn_version
200
from vllm.logger import init_logger
201
from vllm.model_executor.layers.linear import (ColumnParallelLinear,
202
LinearBase, RowParallelLinear,
0 commit comments