bitsandbytes

bitsandbytes enables accessible large language models via k-bit quantization for PyTorch. bitsandbytes provides three main features for dramatically reducing memory consumption for inference and training:

• 8-bit optimizers uses block-wise quantization to maintain 32-bit performance at a small fraction of the memory cost.
• LLM.int8() or 8-bit quantization enables large language model inference with only half the required memory and without any performance degradation. This method is based on vector-wise quantization to quantize most features to 8-bits and separately treating outliers with 16-bit matrix multiplication.
• QLoRA or 4-bit quantization enables large language model training with several memory-saving techniques that don’t compromise performance. This method quantizes a model to 4-bits and inserts a small set of trainable low-rank adaptation (LoRA) weights to allow training.

License

bitsandbytes is MIT licensed.

We thank Fabio Cannizzo for his work on FastBinarySearch which we use for CPU quantization.

< > Update on GitHub