update

Signed-off-by: yewentao256 <zhyanwentao@126.com>

vllm/model_executor/layers/fused_moe/layer.py

@@ -1137,7 +1137,7 @@ class FusedMoE(CustomOp):
             )
             self.local_num_experts = local_num_experts
             self.register_buffer("expert_map", expert_map)
-            logger.debug_once(
+            logger.info_once(
                 "[EP Rank %s/%s] Expert parallelism is enabled. Expert "
                 "placement strategy: %s. Local/global"
                 " number of experts: %s/%s. Experts local to global index map:"

vllm/v1/engine/core.py

@@ -725,6 +725,7 @@ class EngineCoreProc(EngineCore):
         )
 
         # Receive initialization message.
+        logger.debug("Waiting for init message from front-end.")
         if not handshake_socket.poll(timeout=HANDSHAKE_TIMEOUT_MINS * 60_000):
             raise RuntimeError(
                 "Did not receive response from front-end "