Instructions to use replicate/bitsandbytes-mps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/bitsandbytes-mps with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("replicate/bitsandbytes-mps") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from replicate/bitsandbytes-mps: direct link, hf CLI and curl.
- Browser
- Download file 984 Bytes
-
https://huggingface.co/replicate/bitsandbytes-mps/resolve/main/README.md
- Command line
-
hf download hf://replicate/bitsandbytes-mps/README.md
-
curl -L -o README.md https://huggingface.co/replicate/bitsandbytes-mps/resolve/main/README.md
984 Bytes
metadata
library_name: kernels
license: mit
Starting from September 13, 2026, we will be removing the "model" type repositories of kernels (e.g., kernels-community/flash-attn3). Make sure you're using a latest version of kernels. If you face any disruption, please report them here: https://github.com/huggingface/kernels/issues/new.
This is the repository card of kernels-community/bitsandbytes-mps that has been pushed on the Hub. It was built to be used with the kernels library. This card was automatically generated.
How to use
# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel
kernel_module = get_kernel("kernels-community/bitsandbytes-mps")
quantize_4bit = kernel_module.quantize_4bit
quantize_4bit(...)
Available functions
quantize_4bitdequantize_4bitgemv_4bitgemm_4bitlinear_4bit
Benchmarks
No benchmark available yet.