openteamsinc
pypi/nvidia_modelopt
Risk Profile
Package
Source
Risk Profile
Maturity:
Mature
Health:
Healthy
Legal:
Caution Needed
License includes a patent grant clause
Security:
Healthy
Package
pypi
nvidia_modelopt
Version
0.40.0
Last Release Date
about 1 month ago
License
Apache
Dependencies
ninja
numpy
packaging
pydantic
>=2.0
nvidia-ml-py
>=12
rich
scipy
tqdm
pulp
regex
safetensors
torch
>=2.6
torchprofile
>=0.0.4
onnx:
cppimport
cupy-cuda12x
ml_dtypes
onnx-graphsurgeon
onnx
~=1.19.0
onnxconverter-common
~=1.16.0
onnxruntime
~=1.22.0
onnxruntime-gpu
~=1.22.0
onnxruntime-directml
==1.20.0
onnxscript
onnxslim
>=0.1.76
polygraphy
>=0.49.22
hf:
accelerate
>=1.0.0
datasets
>=3.0.0
diffusers
>=0.32.2
huggingface_hub
>=0.24.0
peft
>=0.17.0
transformers
<5.0, >=4.53
deepspeed
>=0.9.6
dev-lint:
bandit
[toml]
==1.7.9
mypy
==1.17.1
pre-commit
==4.3.0
ruff
==0.12.11
dev-test:
coverage
pytest
pytest-cov
pytest-instafail
pytest-timeout
timm
torchvision
torch-geometric
tox
>4.18
tox-current-env
>=0.0.12
dev-docs:
autodoc_pydantic
>=2.1.0
sphinx
~=8.1.0
sphinx-argparse
>=0.5.2
sphinx-autobuild
>=2024.10.3
sphinx-copybutton
>=0.5.2
sphinx-inline-tabs
>=2023.4.21
sphinx-rtd-theme
~=3.0.0
sphinx-togglebutton
>=0.3.2
dev-build:
cython
setuptools
>=80
setuptools-scm
>=8
all:
cppimport
cupy-cuda12x
ml_dtypes
onnx-graphsurgeon
onnx
~=1.19.0
onnxconverter-common
~=1.16.0
onnxruntime
~=1.22.0
onnxruntime-gpu
~=1.22.0
onnxruntime-directml
==1.20.0
onnxscript
onnxslim
>=0.1.76
polygraphy
>=0.49.22
accelerate
>=1.0.0
datasets
>=3.0.0
diffusers
>=0.32.2
huggingface_hub
>=0.24.0
peft
>=0.17.0
transformers
<5.0, >=4.53
deepspeed
>=0.9.6
dev:
cppimport
cupy-cuda12x
ml_dtypes
onnx-graphsurgeon
onnx
~=1.19.0
onnxconverter-common
~=1.16.0
onnxruntime
~=1.22.0
onnxruntime-gpu
~=1.22.0
onnxruntime-directml
==1.20.0
onnxscript
onnxslim
>=0.1.76
polygraphy
>=0.49.22
accelerate
>=1.0.0
datasets
>=3.0.0
diffusers
>=0.32.2
huggingface_hub
>=0.24.0
peft
>=0.17.0
transformers
<5.0, >=4.53
deepspeed
>=0.9.6
bandit
[toml]
==1.7.9
mypy
==1.17.1
pre-commit
==4.3.0
ruff
==0.12.11
coverage
pytest
pytest-cov
pytest-instafail
pytest-timeout
timm
torchvision
torch-geometric
tox
>4.18
tox-current-env
>=0.0.12
autodoc_pydantic
>=2.1.0
sphinx
~=8.1.0
sphinx-argparse
>=0.5.2
sphinx-autobuild
>=2024.10.3
sphinx-copybutton
>=0.5.2
sphinx-inline-tabs
>=2023.4.21
sphinx-rtd-theme
~=3.0.0
sphinx-togglebutton
>=0.3.2
cython
setuptools
>=80
setuptools-scm
>=8
cppimport
cupy-cuda12x
ml_dtypes
onnx-graphsurgeon
onnx
~=1.19.0
onnxconverter-common
~=1.16.0
onnxruntime
~=1.22.0
onnxruntime-gpu
~=1.22.0
onnxruntime-directml
==1.20.0
onnxscript
onnxslim
>=0.1.76
polygraphy
>=0.49.22
accelerate
>=1.0.0
datasets
>=3.0.0
diffusers
>=0.32.2
huggingface_hub
>=0.24.0
peft
>=0.17.0
transformers
<5.0, >=4.53
deepspeed
>=0.9.6
Source
Location
NVIDIA/Model-Optimizer
Last Source Update
4 days ago
Licenses
Apache License 2.0
Distribution Destinations
pypi/nvidia-modelopt
