Skip to content
AI Atlas
LibraryActive

nvidia-modelopt

NVIDIAgithub.com/NVIDIA/Model-Optimizer

Nvidia Model Optimizer: A unified library of SOTA model optimization techniques like quantization, pruning, Neural Architecture Search (NAS), distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, Tensor

quality64

Updated 3 h ago · first seen 11 Sept 2026

lib_01M29ACMJWRC1DW2CVBHEHNMNN

Version
0.46.1
T2 · 3 h ago
Released
9 Sept 2026
T2 · 3 h ago
License
Apache-2.0
T2 · 3 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

15 claims · 15 properties

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0currentcurrentPyPI public package metadataT2mediumdeterministic

Repositoryrepository_url1

Claim history for Repository
ValueValid from → toStatusSourceConfidenceExtractor
https://github.com/NVIDIA/Model-OptimizercurrentcurrentPyPI public package metadataT2mediumdeterministic

Authorauthor1

Claim history for Author
ValueValid from → toStatusSourceConfidenceExtractor
NVIDIA CorporationcurrentcurrentPyPI public package metadataT2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Nvidia Model Optimizer: A unified library of SOTA model optimization techniques like quantization, pruning, Neural Architecture Search (NAS), distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.currentcurrentPyPI public package metadataT2mediumdeterministic

Homepagehomepage1

Claim history for Homepage
ValueValid from → toStatusSourceConfidenceExtractor
https://github.com/NVIDIA/Model-OptimizercurrentcurrentPyPI public package metadataT2mediumdeterministic

Latest releaselatest_release_at1

Claim history for Latest release
ValueValid from → toStatusSourceConfidenceExtractor
9 Sept 2026currentcurrentPyPI public package metadataT2mediumdeterministic

Latest versionlatest_version1

Claim history for Latest version
ValueValid from → toStatusSourceConfidenceExtractor
0.46.1currentcurrentPyPI public package metadataT2mediumdeterministic

Releasesmetric.releases1

Claim history for Releases
ValueValid from → toStatusSourceConfidenceExtractor
39currentcurrentPyPI public package metadataT2mediumdeterministic

PyPIpypi1

Claim history for PyPI
ValueValid from → toStatusSourceConfidenceExtractor
nvidia-modeloptcurrentcurrentPyPI public package metadataT2mediumdeterministic

Pypi licensepypi_license1

Claim history for Pypi license
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0currentcurrentPyPI public package metadataT2mediumdeterministic

Pypi release atpypi_release_at1

Claim history for Pypi release at
ValueValid from → toStatusSourceConfidenceExtractor
9 Sept 2026currentcurrentPyPI public package metadataT2mediumdeterministic

Pypi urlpypi_url1

Claim history for Pypi url
ValueValid from → toStatusSourceConfidenceExtractor
https://pypi.org/project/nvidia-modelopt/currentcurrentPyPI public package metadataT2mediumdeterministic

Pypi versionpypi_version1

Claim history for Pypi version
ValueValid from → toStatusSourceConfidenceExtractor
0.46.1currentcurrentPyPI public package metadataT2mediumdeterministic

Python classifierspython_classifiers1

Claim history for Python classifiers
ValueValid from → toStatusSourceConfidenceExtractor
Programming Language :: Python :: 3.10, Programming Language :: Python :: 3.11, Programming Language :: Python :: 3.12, Programming Language :: Python :: 3.13currentcurrentPyPI public package metadataT2mediumdeterministic

Requires pythonrequires_python1

Claim history for Requires python
ValueValid from → toStatusSourceConfidenceExtractor
<3.15,>=3.10currentcurrentPyPI public package metadataT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →