Kernels:
Trusted publisher
| library_name: kernels | |
| license: mit | |
| This is the repository card of ggml-org/ggml-quantization 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("ggml-org/ggml-quantization", version=1) | |
| GEMV_TYPES = kernel_module.GEMV_TYPES | |
| GEMV_TYPES(...) | |
| ``` | |
| ## Available functions | |
| - `GEMV_TYPES` | |
| - `MAX_GEMV_ROWS` | |
| - `dequantize` | |
| - `get_rows` | |
| - `mul_mat_id` | |
| - `mul_mat_vec` | |
| ## Benchmarks | |
| No benchmark available yet. | |