Factual package intelligence from PyPI

tensorrt-llm 1.2.1 package intelligence

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

pip install tensorrt-llm

Current version
1.2.1
Python requirement
<4,>=3.10
License
Apache License 2.0
Distribution type
No wheel classification available
Release files
1 (0 wheels, 1 source)
Download size
9.9 KiB
Release history
145 releases with files
Median release cadence
7 days

tensorrt-llm dependencies

PyPI declares 118 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. accelerate >=1.7.0
  2. build
  3. colored
  4. cuda-python >=13
  5. diffusers >=0.27.0
  6. lark
  7. mpi4py
  8. numpy <2
  9. onnx <1.20.0,>=1.18.0
  10. onnx_graphsurgeon >=0.5.2
  11. openai
  12. polygraphy
  13. psutil
  14. nvidia-ml-py >=13
  15. pulp
  16. pandas
  17. h5py ==3.12.1
  18. StrEnum
  19. sentencepiece >=0.1.99
  20. tensorrt ~=10.14.1
  21. torch <=2.10.0a0,>=2.9.1
  22. torchvision
  23. nvidia-modelopt ~=0.37.0
  24. nvidia-nccl-cu13 <=2.28.9,>=2.27.7
  25. nvidia-cuda-nvrtc

The compact report shows 25 of 118 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

tensorrt-llm publishes 0 wheels and 1 source archive for version 1.2.1. Wheel platform tags: No wheel platform tags.

Declared Python classifiers: 3.10, 3.12.

Release activity and sources

PyPI lists 145 releases with files. The first dated release is ; 46 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.