tensorrt-llm
| Name | tensorrt-llm JSON |
| Version |
0.17.0.post1
JSON |
| download | |
| home_page | https://github.com/NVIDIA/TensorRT-LLM |
| Summary | TensorRT-LLM: A TensorRT Toolbox for Large Language Models |
| upload_time | 2025-02-02 06:24:04 |
| maintainer | None |
| docs_url | None |
| author | NVIDIA Corporation |
| requires_python | <4,>=3.7 |
| license | Apache License 2.0 |
| keywords | nvidia tensorrt deeplearning inference |
| VCS |  |
| bugtrack_url | |
| requirements | accelerate build colored cuda-python diffusers lark mpi4py numpy onnx onnx_graphsurgeon openai polygraphy psutil pynvml pulp pandas h5py StrEnum sentencepiece tensorrt torch torchvision nvidia-modelopt nvidia-nccl-cu12 nvidia-cuda-nvrtc-cu12 transformers pydantic pillow wheel optimum evaluate mpmath click click_option_group aenum pyzmq fastapi uvicorn httpx setuptools ordered-set peft einops flashinfer-python ffmpeg opencv-python-headless |
| Travis-CI | No Travis. |
| coveralls test coverage | No coveralls. |
TensorRT-LLM: A TensorRT Toolbox for Large Language Models
Raw data
{
"_id": null,
"home_page": "https://github.com/NVIDIA/TensorRT-LLM",
"name": "tensorrt-llm",
"maintainer": null,
"docs_url": null,
"requires_python": "<4,>=3.7",
"maintainer_email": null,
"keywords": "nvidia tensorrt deeplearning inference",
"author": "NVIDIA Corporation",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/2b/c4/2cf29e4e776600235ec541af57eeb618f5f719c4e914cc863c837308b1c6/tensorrt_llm-0.17.0.post1.tar.gz",
"platform": null,
"description": "TensorRT-LLM: A TensorRT Toolbox for Large Language Models\n",
"bugtrack_url": null,
"license": "Apache License 2.0",
"summary": "TensorRT-LLM: A TensorRT Toolbox for Large Language Models",
"version": "0.17.0.post1",
"project_urls": {
"Download": "https://github.com/NVIDIA/TensorRT-LLM/tags",
"Homepage": "https://github.com/NVIDIA/TensorRT-LLM"
},
"split_keywords": [
"nvidia",
"tensorrt",
"deeplearning",
"inference"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2bc42cf29e4e776600235ec541af57eeb618f5f719c4e914cc863c837308b1c6",
"md5": "4883c2b1406b38072e6835718a70330e",
"sha256": "678dfe04b2f638db32a63d966fdb84ff14087bf6aab9a16ff96de196cedec1d9"
},
"downloads": -1,
"filename": "tensorrt_llm-0.17.0.post1.tar.gz",
"has_sig": false,
"md5_digest": "4883c2b1406b38072e6835718a70330e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4,>=3.7",
"size": 762,
"upload_time": "2025-02-02T06:24:04",
"upload_time_iso_8601": "2025-02-02T06:24:04.205371Z",
"url": "https://files.pythonhosted.org/packages/2b/c4/2cf29e4e776600235ec541af57eeb618f5f719c4e914cc863c837308b1c6/tensorrt_llm-0.17.0.post1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-02 06:24:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "NVIDIA",
"github_project": "TensorRT-LLM",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "accelerate",
"specs": [
[
">=",
"0.25.0"
]
]
},
{
"name": "build",
"specs": []
},
{
"name": "colored",
"specs": []
},
{
"name": "cuda-python",
"specs": []
},
{
"name": "diffusers",
"specs": [
[
">=",
"0.27.0"
]
]
},
{
"name": "lark",
"specs": []
},
{
"name": "mpi4py",
"specs": []
},
{
"name": "numpy",
"specs": [
[
"<",
"2"
]
]
},
{
"name": "onnx",
"specs": [
[
">=",
"1.12.0"
]
]
},
{
"name": "onnx_graphsurgeon",
"specs": [
[
">=",
"0.5.2"
]
]
},
{
"name": "openai",
"specs": []
},
{
"name": "polygraphy",
"specs": []
},
{
"name": "psutil",
"specs": []
},
{
"name": "pynvml",
"specs": [
[
">=",
"11.5.0"
]
]
},
{
"name": "pulp",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "h5py",
"specs": [
[
"==",
"3.12.1"
]
]
},
{
"name": "StrEnum",
"specs": []
},
{
"name": "sentencepiece",
"specs": [
[
">=",
"0.1.99"
]
]
},
{
"name": "tensorrt",
"specs": [
[
"~=",
"10.8.0"
]
]
},
{
"name": "torch",
"specs": [
[
">=",
"2.6.0a0"
],
[
"<=",
"2.6.0"
]
]
},
{
"name": "torchvision",
"specs": []
},
{
"name": "nvidia-modelopt",
"specs": [
[
"~=",
"0.23.0"
]
]
},
{
"name": "nvidia-nccl-cu12",
"specs": []
},
{
"name": "nvidia-cuda-nvrtc-cu12",
"specs": []
},
{
"name": "transformers",
"specs": [
[
"<",
"4.48.0"
],
[
">=",
"4.47.0"
]
]
},
{
"name": "pydantic",
"specs": [
[
">=",
"2.9.1"
]
]
},
{
"name": "pillow",
"specs": [
[
"==",
"10.3.0"
]
]
},
{
"name": "wheel",
"specs": []
},
{
"name": "optimum",
"specs": []
},
{
"name": "evaluate",
"specs": []
},
{
"name": "mpmath",
"specs": [
[
">=",
"1.3.0"
]
]
},
{
"name": "click",
"specs": []
},
{
"name": "click_option_group",
"specs": []
},
{
"name": "aenum",
"specs": []
},
{
"name": "pyzmq",
"specs": []
},
{
"name": "fastapi",
"specs": [
[
"==",
"0.115.4"
]
]
},
{
"name": "uvicorn",
"specs": []
},
{
"name": "httpx",
"specs": []
},
{
"name": "setuptools",
"specs": []
},
{
"name": "ordered-set",
"specs": []
},
{
"name": "peft",
"specs": []
},
{
"name": "einops",
"specs": []
},
{
"name": "flashinfer-python",
"specs": [
[
"~=",
"0.2.0"
]
]
},
{
"name": "ffmpeg",
"specs": []
},
{
"name": "opencv-python-headless",
"specs": []
}
],
"lcname": "tensorrt-llm"
}
