diff --git a/tensorrt_llm/_torch/pyexecutor/py_executor.py b/tensorrt_llm/_torch/pyexecutor/py_executor.py index 3ab3b8d4f6d9..0ba05b9dbb4e 100644 --- a/tensorrt_llm/_torch/pyexecutor/py_executor.py +++ b/tensorrt_llm/_torch/pyexecutor/py_executor.py @@ -3256,6 +3256,7 @@ def _handle_dynamic_draft_len(self, if spec_config is not None and spec_config.is_linear_tree else self.model_engine.max_total_draft_tokens) + @nvtx_range("_can_queue") def _can_queue(self, scheduled_batch): # can_queue_this_rank is for case that the batch is not empty on this rank, but empty on other ranks @@ -3860,6 +3861,7 @@ def _check_benchmark_disagg_gate(self, scheduled_batch: ScheduledRequests, return can_forward, True return can_forward, False + @nvtx_range("_handle_disagg_cache_errors_synced") def _handle_disagg_cache_errors_synced(self): """Rank-safe disagg cache error and poison handler.