Shanmugamr1992/megatron inference ultra (#3784)

Co-authored-by: Teodor-Dumitru Ene <teodord.ene@gmail.com>
Co-authored-by: Robert Kirby <rkirby@nvidia.com>
Co-authored-by: Shanmugam Ramasamy <shanmugamr@cw-dfw-cs-001-login-01.cm.cluster>
Co-authored-by: rislam <rislam@nvidia.com>

Author: 5 people

megatron/core/inference/engines/dynamic_engine.py

@@ -884,7 +884,10 @@ def _add_request(
             self.failed_request_ids.append(request_id)
             if self.rank == 0:
                 warnings.warn(
-                    f"Request {request_id} failed to be added to the engine due to errors."
+                    f"Request {request_id} failed to be added to the engine due to errors. "
+                    f"Prompt Tokens: {len(request.prompt_tokens)} "
+                    f"Tokens to generate: {request.sampling_params.num_tokens_to_generate} "
+                    f"Max sequence length: {self.context.max_sequence_length} "
                 )
 
         return self.requests[request_id].future