tensorrt-llm
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/c6/1f/b8af3cb71b85d97aec496bd95e4f07cf97b50e8d4edc2b810186181d595f/tensorrt_llm-1.0.0.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": "1.0.0",
"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": "c61fb8af3cb71b85d97aec496bd95e4f07cf97b50e8d4edc2b810186181d595f",
"md5": "19660b10d12820222e8e61afd3f456ac",
"sha256": "ac6e05bab7371f5f7d706bf0f48c3cdedb06ccf7783fdade63d1f491ab239fe9"
},
"downloads": -1,
"filename": "tensorrt_llm-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "19660b10d12820222e8e61afd3f456ac",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4,>=3.7",
"size": 1649,
"upload_time": "2025-09-24T03:07:21",
"upload_time_iso_8601": "2025-09-24T03:07:21.726531Z",
"url": "https://files.pythonhosted.org/packages/c6/1f/b8af3cb71b85d97aec496bd95e4f07cf97b50e8d4edc2b810186181d595f/tensorrt_llm-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-24 03:07:21",
"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": [
[
">=",
"1.7.0"
]
]
},
{
"name": "build",
"specs": []
},
{
"name": "colored",
"specs": []
},
{
"name": "cuda-python",
"specs": [
[
">=",
"13"
]
]
},
{
"name": "diffusers",
"specs": [
[
">=",
"0.27.0"
]
]
},
{
"name": "lark",
"specs": []
},
{
"name": "mpi4py",
"specs": []
},
{
"name": "numpy",
"specs": [
[
"<",
"2"
]
]
},
{
"name": "onnx",
"specs": [
[
">=",
"1.18.0"
]
]
},
{
"name": "onnx_graphsurgeon",
"specs": [
[
">=",
"0.5.2"
]
]
},
{
"name": "openai",
"specs": []
},
{
"name": "polygraphy",
"specs": []
},
{
"name": "psutil",
"specs": []
},
{
"name": "nvidia-ml-py",
"specs": [
[
">=",
"13"
]
]
},
{
"name": "pulp",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "h5py",
"specs": [
[
"==",
"3.12.1"
]
]
},
{
"name": "StrEnum",
"specs": []
},
{
"name": "sentencepiece",
"specs": [
[
">=",
"0.1.99"
]
]
},
{
"name": "tensorrt",
"specs": [
[
"~=",
"10.13.0"
]
]
},
{
"name": "torch",
"specs": [
[
"<=",
"2.8.0"
],
[
">=",
"2.8.0a0"
]
]
},
{
"name": "torchvision",
"specs": []
},
{
"name": "nvidia-modelopt",
"specs": [
[
"~=",
"0.33.0"
]
]
},
{
"name": "nvidia-nccl-cu13",
"specs": []
},
{
"name": "nvidia-cuda-nvrtc",
"specs": []
},
{
"name": "transformers",
"specs": [
[
"==",
"4.56.0"
]
]
},
{
"name": "prometheus_client",
"specs": []
},
{
"name": "prometheus_fastapi_instrumentator",
"specs": []
},
{
"name": "pydantic",
"specs": [
[
">=",
"2.9.1"
]
]
},
{
"name": "pydantic-settings",
"specs": []
},
{
"name": "omegaconf",
"specs": []
},
{
"name": "pillow",
"specs": [
[
"==",
"10.3.0"
]
]
},
{
"name": "wheel",
"specs": [
[
"<=",
"0.45.1"
]
]
},
{
"name": "optimum",
"specs": []
},
{
"name": "datasets",
"specs": [
[
"==",
"3.1.0"
]
]
},
{
"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": [
[
"<=",
"0.117.1"
],
[
">=",
"0.115.4"
]
]
},
{
"name": "uvicorn",
"specs": []
},
{
"name": "setuptools",
"specs": [
[
"<",
"80"
]
]
},
{
"name": "ordered-set",
"specs": []
},
{
"name": "peft",
"specs": []
},
{
"name": "patchelf",
"specs": []
},
{
"name": "einops",
"specs": []
},
{
"name": "flashinfer-python",
"specs": [
[
">=",
"0.3.0"
],
[
"<",
"0.4.0"
]
]
},
{
"name": "opencv-python-headless",
"specs": []
},
{
"name": "xgrammar",
"specs": [
[
"==",
"0.1.25"
]
]
},
{
"name": "llguidance",
"specs": [
[
"==",
"0.7.29"
]
]
},
{
"name": "jsonschema",
"specs": []
},
{
"name": "backoff",
"specs": []
},
{
"name": "nvtx",
"specs": []
},
{
"name": "matplotlib",
"specs": []
},
{
"name": "meson",
"specs": []
},
{
"name": "ninja",
"specs": []
},
{
"name": "etcd3",
"specs": []
},
{
"name": "blake3",
"specs": []
},
{
"name": "soundfile",
"specs": []
},
{
"name": "triton",
"specs": [
[
"==",
"3.3.1"
]
]
},
{
"name": "tiktoken",
"specs": []
},
{
"name": "blobfile",
"specs": []
},
{
"name": "openai-harmony",
"specs": [
[
"==",
"0.0.4"
]
]
},
{
"name": "nvidia-cutlass-dsl",
"specs": [
[
"==",
"4.2.1"
]
]
},
{
"name": "numba-cuda",
"specs": [
[
">=",
"0.19.0"
]
]
},
{
"name": "plotly",
"specs": []
},
{
"name": "numexpr",
"specs": [
[
"<",
"2.14.0"
]
]
}
],
"lcname": "tensorrt-llm"
}
