|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
# LTX-Q8-Kernels Pre-built Wheel |
|
|
|
|
|
This repository contains pre-built wheel files for the LTX-Q8-Kernels to avoid the need for building on SM89 instances with Python 3.11. |
|
|
|
|
|
## Quick Install |
|
|
|
|
|
Instead of building the kernels from source (which requires SM89 compute capability), you can directly install the pre-built wheel: |
|
|
|
|
|
```bash |
|
|
pip install https://huggingface.co/ModelsLab/LTX-Q8-Kernels-build-ada/resolve/main/q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl |
|
|
``` |
|
|
|
|
|
## Requirements |
|
|
|
|
|
- **Python**: 3.11 |
|
|
- **Platform**: Linux x86_64 |
|
|
- **CUDA**: Compatible CUDA installation |
|
|
- **Architecture**: Built for Ada Lovelace (RTX 40 series) and compatible GPUs |
|
|
|
|
|
## Usage |
|
|
|
|
|
After installation, you can import and use the kernels in your LTX-Video projects: |
|
|
|
|
|
```python |
|
|
import q8_kernels |
|
|
# Your LTX-Video code here |
|
|
``` |
|
|
|
|
|
## Benefits |
|
|
|
|
|
- **No SM89 Build Requirements**: Skip the complex build process that requires specific GPU compute capabilities |
|
|
- **Faster Setup**: Direct installation without compilation time |
|
|
- **Pre-optimized**: Built with optimal settings for Ada Lovelace architecture |
|
|
|
|
|
## Compatibility |
|
|
|
|
|
This wheel is specifically built for: |
|
|
- **Python 3.11** (`cp311-cp311`) |
|
|
- **Linux x86_64** systems |
|
|
- **Ada Lovelace GPU architecture** (RTX 4090, RTX 4080, etc.) |
|
|
|
|
|
## Alternative Installation Methods |
|
|
|
|
|
### From Hugging Face Hub |
|
|
|
|
|
```bash |
|
|
# Using huggingface_hub |
|
|
pip install huggingface_hub |
|
|
python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='ModelsLab/LTX-Q8-Kernels-build-ada', filename='q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl', local_dir='.')" |
|
|
pip install q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl |
|
|
``` |
|
|
|
|
|
### Download and Install |
|
|
|
|
|
```bash |
|
|
wget https://huggingface.co/ModelsLab/LTX-Q8-Kernels-build-ada/resolve/main/q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl |
|
|
pip install q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl |
|
|
``` |
|
|
|
|
|
## Troubleshooting |
|
|
|
|
|
If you encounter issues: |
|
|
|
|
|
1. **Verify Python version**: `python --version` should show 3.11.x |
|
|
2. **Check platform**: This wheel only works on Linux x86_64 |
|
|
3. **CUDA compatibility**: Ensure you have a compatible CUDA installation |
|
|
4. **GPU support**: Verify your GPU supports the required compute capability |
|
|
|
|
|
## Building from Source (Alternative) |
|
|
|
|
|
If you need to build from source or for different architectures, refer to the main [LTX-Video repository](https://github.com/Lightricks/LTX-Video) for build instructions. |
|
|
|
|
|
## Version Information |
|
|
|
|
|
- **Package Version**: 0.0.5 |
|
|
- **Python**: 3.11 |
|
|
- **Platform**: linux_x86_64 |
|
|
- **Build Target**: Ada Lovelace (SM89) |
|
|
|
|
|
## License |
|
|
|
|
|
This package follows the same license as the original LTX-Video project. |
