Revert "drop ascend scheduler" (#4580)

Reverts vllm-project/vllm-ascend#4498
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

vllm_ascend/torchair/torchair_attention.py

@@ -451,7 +451,8 @@ class AscendAttentionTorchairBackendImpl(AttentionImpl):
         else:
             raise NotImplementedError(
                 "Torchair graph mode with non-MLA attention backend is still experimental."
-                "v1 scheduler(chunked prefill) is not supported at this moment. "
-            )
+                "v1 scheduler(chunked prefill) is not supported at this moment. Please"
+                "setting 'ascend_scheduler_config':{'enabled':true} in additional_config"
+                "to use ascend scheduler.")
 
         return output.view(num_tokens, self.hidden_size)