update common.py

vllm/v1/attention/backends/mla/common.py

@@ -1138,7 +1138,10 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]):
     ) -> torch.Tensor:
         assert attn_metadata.prefill is not None
 
-        has_context = attn_metadata.prefill.chunked_context is not None
+        if envs.VLLM_HAS_CONTEXT_DEFAULT:
+            has_context = attn_metadata.prefill.chunked_context is not None
+        else:
+            has_context = False
         kv_nope = self.kv_b_proj(kv_c_normed)[0].view(\
             -1, self.num_heads, self.qk_nope_head_dim + self.v_head_dim)
         k_nope, v = kv_nope\