Factual package intelligence from PyPI

torch-tensorrt 2.12.1 package intelligence

Torch-TensorRT is a package which allows users to automatically compile PyTorch and TorchScript modules to TensorRT while remaining in PyTorch

pip install torch-tensorrt

Current version
2.12.1
Python requirement
>=3.10
License
BSD License
Distribution type
Includes compiled wheel
Release files
12 (12 wheels, 0 source)
Download size
36.4 MiB
Release history
17 releases with files
Median release cadence
77 days

torch-tensorrt dependencies

PyPI declares 9 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. packaging >=23
  2. typing-extensions >=4.7.0
  3. filelock
  4. dllist
  5. psutil
  6. numpy
  7. torch <2.13.0,>=2.12.0
  8. executorch >=1.2.0 when sys_platform == "linux"
  9. tensorrt <10.17.0,>=10.16.1

Compatibility and release files

torch-tensorrt publishes 12 wheels and 0 source archives for version 2.12.1. Wheel platform tags: manylinux_2_28_aarch64, manylinux_2_28_x86_64, win_amd64.

No version-specific Python classifiers are declared.

Release activity and sources

PyPI lists 17 releases with files. The first dated release is ; 6 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .

1 historical release is fully yanked in PyPI metadata.