From ea49afdf0b29673bcf9c95c561acbff9c8c38a0e Mon Sep 17 00:00:00 2001 From: Dmitry Barsukoff Date: Mon, 2 Feb 2026 03:41:15 +0300 Subject: [PATCH] [None][fix] AttributeError with return_perf_metrics on tensorrt backend (#10662) Signed-off-by: Dmitry Barsukoff Co-authored-by: Kanghwan <861393+karljang@users.noreply.github.com> --- tensorrt_llm/llmapi/llm_args.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tensorrt_llm/llmapi/llm_args.py b/tensorrt_llm/llmapi/llm_args.py index eac238bb0a..7286ced1f0 100644 --- a/tensorrt_llm/llmapi/llm_args.py +++ b/tensorrt_llm/llmapi/llm_args.py @@ -2182,6 +2182,12 @@ class BaseLlmArgs(StrictBaseModel): description="Return perf metrics.", status="prototype") + perf_metrics_max_requests: int = Field( + default=0, + description= + "The maximum number of requests for perf metrics. Must also set return_perf_metrics to true to get perf metrics.", + status="prototype") + orchestrator_type: Optional[Literal["rpc", "ray"]] = Field( default=None, description= @@ -2898,12 +2904,6 @@ class TorchLlmArgs(BaseLlmArgs): description="Print iteration logs.", status="beta") - perf_metrics_max_requests: int = Field( - default=0, - description= - "The maximum number of requests for perf metrics. Must also set request_perf_metrics to true to get perf metrics.", - status="prototype") - batch_wait_timeout_ms: float = Field( default=0, description=