kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-04 18:21:52 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][fix] AttributeError with return_perf_metrics on tensorrt backend (#10662)

Browse Source 
Signed-off-by: Dmitry Barsukoff <riZZZhik@gmail.com>
Co-authored-by: Kanghwan <861393+karljang@users.noreply.github.com>
This commit is contained in:
Dmitry Barsukoff 2026-02-02 03:41:15 +03:00 committed by GitHub
parent 1c8f8bed00
commit ea49afdf0b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tensorrt_llm/llmapi/llm_args.py
View File

@ -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=