tensorrt-llm
pypiv1.2.1TensorRT 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.
License Apache License 2.0permissive141 versions1 maintainers118 deps
NVIDIA/TensorRT-LLM75
/ 100
Health
safe to use
[email protected] is safe to use (health: 75/100)
Health breakdown0 – 100
25/25
maintenance
0/20
popularity
25/25
security
15/15
maturity
10/15
community
Vulnerabilities
0
none known
Health History
Dependency Tree
License Audit
Dependencies (118)
acceleratebuildcoloredcuda-pythondiffuserslarkmpi4pynumpyonnxonnx_graphsurgeonopenaipolygraphypsutilnvidia-ml-pypulppandash5pyStrEnumsentencepiecetensorrt~torchtorchvisionnvidia-modelopt[torch]~nvidia-nccl-cu13nvidia-cuda-nvrtctransformersprometheus_clientprometheus_fastapi_instrumentatorpydanticpydantic-settings[yaml]omegaconfpillowoptimumdatasetsevaluatempmathclickclick_option_groupaenumpyzmqfastapistarletteuvicornsetuptoolsordered-setpeftpatchelfeinopsflashinfer-pythonopencv-python-headlessxgrammarllguidancejsonschemabackoffnvtxmatplotlibmesonninjablake3soundfile
API access
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/pypi/tensorrt-llmLast updated · 2026-04-20T09:20:02.047466Z