xx

Author: wangxiaoxin-sherie

vllm_ascend/worker/model_runner_v1.py

@@ -420,7 +420,7 @@ def __init__(self, vllm_config: VllmConfig, device: torch.device):
                                     device=self.device)
 
         if self.vllm_config.model_config.use_mla and \
-            self.compilation_config.cudagraph_mode == CUDAGraphMode.FULL_DECODE_ONLY:
+            self.compilation_config.cudagraph_mode.has_full_cudagraphs():
             rope_dim = self.model_config.hf_text_config.qk_rope_head_dim
             self.cos = torch.ones(self.max_num_reqs *
                                   self.decode_token_per_req,