Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,8 @@ Intel Neural Compressor supports PyTorch with CPU, GPU and HPU. Please install t
pip install neural-compressor-pt
# Framework extension API + TensorFlow dependency
pip install neural-compressor-tf
# Framework extension API + JAX dependency, available since v3.8
# JAX only support build from source installation method before [PyPI support](https://github.com/pypi/support/issues/10012) is available
INC_JAX_ONLY=1 pip install .
# Framework extension API + JAX dependency
pip install neural-compressor-jax
```
**Note**: Further installation methods can be found under [Installation Guide](./docs/source/installation_guide.md). check out our [FAQ](./docs/source/faq.md) for more details.

Expand Down
4 changes: 4 additions & 0 deletions docs/source/installation_guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,10 @@ pip install neural-compressor-pt
# Framework extension API + TensorFlow dependency
pip install neural-compressor-tf
```
```Shell
# Framework extension API + JAX dependency, available since v3.9
pip install neural-compressor-jax
```

### Install from Source
The latest code on main branch may not be stable. Please switch to the latest release tag for better stability. Feel free to open an [issue](https://github.com/intel/neural-compressor/issues) if you encounter an error.
Expand Down
7 changes: 6 additions & 1 deletion examples/jax/keras/gemma/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,12 @@ This document describes quantization of Keras Gemma models using Neural Compress
It is worth conducting experiments in a separate environment. For example, you can use the conda environment from [conda-forge](https://github.com/conda-forge/miniforge). The binary for your environment could be found here: [miniforge](https://github.com/conda-forge/miniforge/releases/latest)

## 2. Install modules
Install Neural Compressor from the source code:

Since Neural Compressor v3.9, you can install the required binaries from PyPI:
```bash
pip install -r requirements.txt
```
Alternatively, you can always install Neural Compressor from the source code:
```bash
pushd ../../../.. # go to the root directory of the Neural Compressor source code
INC_JAX_ONLY=1 pip install .
Expand Down
1 change: 1 addition & 0 deletions examples/jax/keras/gemma/requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
neural-compressor-jax
4 changes: 2 additions & 2 deletions examples/jax/keras/vit/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,11 +10,11 @@ It is worth conducting experiments in a separate environment. For example, you c

## 2. Install modules

Install requirements:
Since Neural Compressor v3.9, you can install the required binaries from PyPI:
```bash
pip install -r requirements.txt
```
Install Neural Compressor from the source code:
Alternatively, you can always install Neural Compressor from the source code:
```bash
pushd ../../../.. # go to the root directory of the Neural Compressor source code
INC_JAX_ONLY=1 pip install .
Expand Down
1 change: 1 addition & 0 deletions examples/jax/keras/vit/requirements.txt
Original file line number Diff line number Diff line change
@@ -1 +1,2 @@
neural-compressor-jax
tensorflow
Loading