Kernels:
Trusted publisher
|
Download README.md from kernels-staging/gemma-quant-kernels: direct link, hf CLI and curl.
- Browser
- Download file 714 Bytes
-
https://huggingface.co/kernels/kernels-staging/gemma-quant-kernels/resolve/main/README.md
- Command line
-
hf download hf://kernels-staging/gemma-quant-kernels/README.md
-
curl -L -o README.md https://huggingface.co/kernels/kernels-staging/gemma-quant-kernels/resolve/main/README.md
714 Bytes
| library_name: kernels | |
| license: apache-2.0 | |
| This is the repository card of kernels-community/gemma-quant-kernels that has been pushed on the Hub. It was built to be used with the [`kernels` library](https://github.com/huggingface/kernels). This card was automatically generated. | |
| ## How to use | |
| ```python | |
| # make sure `kernels` is installed: `pip install -U kernels` | |
| from kernels import get_kernel | |
| kernel_module = get_kernel("kernels-community/gemma-quant-kernels", version=1) | |
| lowbit_gemm = kernel_module.lowbit_gemm | |
| lowbit_gemm(...) | |
| ``` | |
| ## Available functions | |
| - `lowbit_gemm` | |
| - `grouped_lowbit_gemm` | |
| - `pack_int2` | |
| - `pack_int4` | |
| - `unpack_int2` | |
| - `unpack_int4` | |
| ## Benchmarks | |
| No benchmark available yet. | |