Support PyTorch model conversion with LiteRT.
Project Links
Meta
Requires Python: >=3.10
Classifiers
Development Status
- 4 - Beta
Intended Audience
- Developers
- Education
- Science/Research
License
- OSI Approved :: Apache Software License
Programming Language
- Python :: 3
- Python :: 3 :: Only
- Python :: 3.10
- Python :: 3.11
- Python :: 3.12
- Python :: 3.13
Topic
- Scientific/Engineering
- Scientific/Engineering :: Mathematics
- Scientific/Engineering :: Artificial Intelligence
- Software Development
- Software Development :: Libraries
- Software Development :: Libraries :: Python Modules
Library that supports converting PyTorch models into a .tflite format, which can then be run with LiteRT. This enables applications for Android, iOS and IOT that can run models completely on-device.
Install steps and additional details are in the LiteRT Torch GitHub repository.
Wheel compatibility matrix
Files in release
Extras:
None
Dependencies:
absl-py
numpy
scipy
safetensors
multipledispatch
transformers
kagglehub
tabulate
torch
(<2.13.0,>=2.4.0)
ai-edge-litert[model-utils]
(<2.2.0,>=2.1.6)
ai-edge-quantizer
(==0.8.*)
litert-converter
(==0.3.*)
torchao
(>=0.17.0)
jax
jaxtyping
fire
sentencepiece
rich
litert-lm-builder
(>=0.0.0.dev0)