Skip to content

Releases: google-ai-edge/ai-edge-torch

v0.2.0

02 Aug 21:05
@chunnienc chunnienc
v0.2.0
f7585fe
Compare
Choose a tag to compare
v0.2.0 Latest
Latest

Installation and Dependencies

pip install ai-edge-torch==0.2.0
  • Python versions: 3.9, 3.10, 3.11
  • Operating system: Linux
  • PyTorch: 2.4.0
  • TensorFlow: tf-nightly>=2.18.0.dev20240722

See this section of the README

PyTorch Converter

Compatible with torch 2.4.0 stable release. pip install ai-edge-torch(-nightly) is now the only command needed to install ai-edge-torch and all dependencies.

Features

  • Added ai_edge_torch.to_channel_last_io API (doc)
  • Added ai_edge_torch.debug._search_model API

Performance Improvements

  • Improved layout optimization algorithm and general model performance
  • Improved performance for torch.nn.function.interpolate with nearest mode
  • Improved performance for aten.gelu
  • Improved performance for aten.avg_pool2d with ceil_mode=True
  • Reduced conversion memory usage in torch_xla and MLIR converter

Bug Fix

  • Fixed numerical/precision issue with aten.native_group_norm (nn.GroupNorm)

Generative API

Authoring API

Support for new models

Quantization

Documentation

Assets 3
Loading

v0.1.1

14 May 16:38
@advaitjain advaitjain
v0.1.1
875f2ea
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.1.1

Installation and Dependencies

pip install -r https://github.com/google-ai-edge/ai-edge-torch/releases/download/v0.1.1/requirements.txt
pip install ai-edge-torch==0.1.1
  • Python versions: 3.9, 3.10, 3.11
  • Operating system: Linux
  • PyTorch: 2.4.0.dev20240429
  • TensorFlow: 2.17.0.dev20240509

See this section of the README

PyTorch Converter (Beta)

Functionality

First release of a direct path from PyTorch to the TFLite runtime (blog post).

Coverage

Performance

  • Excellent CPU performance for the converted models, leveraging the TFLite XNNPACK delegate.
  • A subset of the Beta test set can be fully delegated to GPU, others are partially delegated or unsupported.
  • QNN delegate (available here) supports most models in the Beta test set with significant average acceleration relative to CPU (20X) and GPU (5X) using Qualcomm’s DSP and neural processing units.

Quantization

  • Support for dynamic quantization with PT2E.
  • Support for post-training quantization via the TFLite converter.
  • AI Edge Torch Converter APIs to use these two quantization frameworks are here.

Known Issues

  • Inference latency with quantized models is higher than unquantized models in some cases.

Generative API (Alpha)

Functionality

  • Provides PyTorch native building blocks to compose LLMs using mobile friendly abstractions for performant execution on TFLite runtime.
  • Examples to author LLMs via Edge Generative API for conversion to TFLite for Gemma, TinyLlama and Phi-2. (Examples)
  • Supports 8-bit dynamic range quantization. (here)
  • Integration with MediaPipe LLM Inference API for easy integration into Mobile Apps, and a prompt interface.

Known Issues

  • The conversion, and serialization process is unoptimized for LLMs. It requires keeping multiple copies of the weights in memory for transformations, and serialization/deserialization.
  • Runtime execution of the LLM in TFLite is missing some memory optimizations, and inefficient during memory unpacking on XNNPack.
Assets 4
Loading