| Name | Version | Summary | date |
| vector-quantize-pytorch |
1.14.43 |
Vector Quantization - Pytorch |
2024-06-29 02:38:36 |
| ai-edge-quantizer-nightly |
0.0.1.dev202406290009 |
A quantizer for advanced developers to quantize converted AI Edge models. |
2024-06-29 00:09:41 |
| sparseml-nightly |
1.8.0.20240628 |
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models |
2024-06-28 20:39:15 |
| optimum-quanto |
0.2.2 |
A pytorch quantization backend for optimum. |
2024-06-28 15:25:10 |
| optimum-intel |
1.18.0 |
Optimum Library is an extension of the Hugging Face Transformers library, providing a framework to integrate third-party libraries from Hardware Partners and interface with their specific functionality. |
2024-06-26 23:21:42 |
| sparseml |
1.8.0 |
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models |
2024-06-21 15:53:30 |
| sparsezoo |
1.8.0 |
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes |
2024-06-21 15:47:37 |
| ai-edge-quantizer |
0.0.1 |
A quantizer for advanced developers to quantize converted ODML models. |
2024-06-03 23:31:26 |
| optimum |
1.20.0 |
Optimum Library is an extension of the Hugging Face Transformers library, providing a framework to integrate third-party libraries from Hardware Partners and interface with their specific functionality. |
2024-05-29 14:30:48 |
| quanto |
0.2.0 |
A quantization toolkit for pytorch. |
2024-05-24 10:49:08 |
| optimum-benchmark |
0.2.1 |
Optimum-Benchmark is a unified multi-backend utility for benchmarking Transformers, Timm, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes. |
2024-05-17 09:25:34 |
| grag |
0.0.1 |
A simple package for implementing RAG |
2024-05-09 21:21:22 |
| sparsezoo-nightly |
1.8.0.20240506 |
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes |
2024-05-06 19:37:51 |
| autoawq |
0.2.5 |
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. |
2024-05-02 18:32:41 |
| nncf |
2.10.0 |
Neural Networks Compression Framework |
2024-04-25 12:01:53 |