compressed-tensors
Library for utilization of compressed safetensors of neural network models
Library for utilization of compressed safetensors of neural network models
To install this package, run one of the following:
The compressed-tensors library extends the safetensors format, providing a versatile and efficient way to store and manage compressed tensor data. This library supports various quantization and sparsity schemes, making it a unified format for handling different model optimizations like GPTQ, AWQ, SmoothQuant, INT8, FP8, SparseGPT, and more.
Summary
Library for utilization of compressed safetensors of neural network models
Last Updated
Jan 7, 2026 at 00:40
License
Apache-2.0
Total Downloads
36
Supported Platforms
GitHub Repository
https://github.com/vllm-project/compressed-tensorsDocumentation
https://github.com/vllm-project/compressed-tensors