kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

cache_transceiver_config (#4556)

Browse Source 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
This commit is contained in:
Chuang Zhu 2025-05-22 13:59:51 +08:00 committed by GitHub
parent e741d2b8d0
commit 3410508020
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorrt_llm/llmapi/llm.py
View File

@ -609,7 +609,7 @@ class LLM:
if self._on_trt_backend and self.args.extended_runtime_perf_knob_config is not None:
executor_config.extended_runtime_perf_knob_config = PybindMirror.maybe_to_pybind(
self.args.extended_runtime_perf_knob_config)
if self._on_trt_backend and self.args.cache_transceiver_config is not None:
if self.args.cache_transceiver_config is not None:
executor_config.cache_transceiver_config = PybindMirror.maybe_to_pybind(
self.args.cache_transceiver_config)
from tensorrt_llm._torch.pyexecutor.config import update_executor_config