kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 07:53:55 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][chore] Remove outdated comment in model_engine.py (#11240)

Browse Source 
Signed-off-by: Harris Nover <249353502+hnover-nv@users.noreply.github.com>
This commit is contained in:
Harris Nover 2026-02-05 11:54:46 -07:00 committed by GitHub
parent d778b26062
commit a7494a5ff4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tensorrt_llm/_torch/pyexecutor/model_engine.py
View File

@ -254,7 +254,6 @@ class PyTorchModelEngine(ModelEngine):
torch_compile_max_num_streams = self.torch_compile_config.max_num_streams if self.torch_compile_config is not None else TorchCompileConfig.model_fields[
'max_num_streams'].default
# Eagle3 draft model now does not support torch.compile
self._torch_compile_enabled = torch_compile_enabled
self._torch_compile_piecewise_cuda_graph = torch_compile_piecewise_cuda_graph