jp6/cu126/: tensorrt-llm-0.12.0 metadata and description
Homepage
Simple index
TensorRT-LLM: A TensorRT Toolbox for Large Language Models
| author |
NVIDIA Corporation |
| classifiers |
- Development Status :: 4 - Beta
- Intended Audience :: Developers
- Programming Language :: Python :: 3.10
|
| download_url |
https://github.com/NVIDIA/TensorRT-LLM/tags |
| keywords |
nvidia tensorrt deeplearning inference |
| license |
Apache License 2.0 |
| requires_dist |
- accelerate>=0.25.0
- build
- colored
- cuda-python
- diffusers>=0.27.0
- lark
- numpy<2
- onnx>=1.12.0
- polygraphy
- psutil
- pulp
- pandas
- h5py==3.10.0
- StrEnum
- sentencepiece>=0.1.99
- torch@ https://developer.download.nvidia.cn/compute/redist/jp/v61/pytorch/torch-2.5.0a0+872d972e41.nv24.08.17622132-cp310-cp310-linux_aarch64.whl
- nvidia-modelopt~=0.15.0
- transformers>=4.38.2
- pillow==10.2.0
- wheel
- optimum
- evaluate
- janus
- mpmath>=1.3.0
- click; extra == "benchmarking"
- pydantic; extra == "benchmarking"
- datasets==2.19.2; extra == "devel"
- einops; extra == "devel"
- graphviz; extra == "devel"
- mypy; extra == "devel"
- parameterized; extra == "devel"
- pre-commit; extra == "devel"
- pybind11; extra == "devel"
- pybind11-stubgen; extra == "devel"
- pytest-cov; extra == "devel"
- pytest-forked; extra == "devel"
- pytest-xdist; extra == "devel"
- rouge-score; extra == "devel"
- cloudpickle; extra == "devel"
- typing-extensions==4.8.0; extra == "devel"
- bandit==1.7.7; extra == "devel"
- jsonlines==4.0.0; extra == "devel"
- jieba==0.42.1; extra == "devel"
- rouge==1.0.1; extra == "devel"
|
| requires_python |
>=3.7, <4 |
Because this project isn't in the mirror_whitelist,
no releases from root/pypi are included.
TensorRT-LLM: A TensorRT Toolbox for Large Language Models