[Ascend] optimize Qwen-vl on Ascend (#10556)
Co-authored-by: wangqihui01 <wangqh10@163.com>
This commit is contained in:
co-authored by
wangqihui01
parent
d27a6f7092
commit
095093ee5a
@@ -1840,7 +1840,7 @@ class ServerArgs:
|
||||
parser.add_argument(
|
||||
"--mm-attention-backend",
|
||||
type=str,
|
||||
choices=["sdpa", "fa3", "triton_attn"],
|
||||
choices=["sdpa", "fa3", "triton_attn", "ascend_attn"],
|
||||
default=ServerArgs.mm_attention_backend,
|
||||
help="Set multimodal attention backend.",
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user