Skip to content

GitLab

Commit d2feb104 authored by wujl5's avatar wujl5
Browse files

去掉DTBmm的一个冗余条件

parent 0c7b96c4
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
vllm/v1/attention/backends/mla/common.py
View file @ d2feb104
...@@ -936,7 +936,6 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]): ...@@ -936,7 +936,6 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]):
def enable_fused_DTBmm(self): def enable_fused_DTBmm(self):
if envs.VLLM_USE_FUSED_DTBMM and \ if envs.VLLM_USE_FUSED_DTBMM and \
self.kv_cache_dtype == "fp8_e4m3" and \
torch.cuda.get_device_properties("cuda").gcnArchName.split(':')[0] == "gfx938": torch.cuda.get_device_properties("cuda").gcnArchName.split(':')[0] == "gfx938":
return True return True
else: else:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment