去掉DTBmm的一个冗余条件

d2feb104 · wujl5 · 0c7b96c4 · d2feb104
Commit d2feb104 authored Feb 06, 2026 by wujl5
Show whitespace changes
Inline Side-by-side

Showing with 0 additions and 1 deletion

vllm/v1/attention/backends/mla/common.py vllm/v1/attention/backends/mla/common.py +0 -1

No files found.
--- a/vllm/v1/attention/backends/mla/common.py
+++ b/vllm/v1/attention/backends/mla/common.py
@@ -936,7 +936,6 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]):
        
    def enable_fused_DTBmm(self):
        if envs.VLLM_USE_FUSED_DTBMM and \
-            self.kv_cache_dtype == "fp8_e4m3" and \
                torch.cuda.get_device_properties("cuda").gcnArchName.split(':')[0] == "gfx938":
            return True
        else: