Instructions to use replicate/quantization-eetq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/quantization-eetq with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/quantization-eetq", version=1) - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update input
6337ee0 -
Use default capabilities
88a5927
-
Fix flake input
0959f8f -
Build (aarch64)
8f7b5f0 -
Build
dffc953 -
Update flake
f87291e -
Add extra capabilities
6662cb4
-
feat: update to include rev in kernel for reproducible symbols
drbh33c188c
-
Update for build.toml changes
34fd1ec
-
Update README.md (#1)
Verified signature- Update README.md (e7c03158b3d531d9912070897c4bb1f5d9aecd97) Co-authored-by: Lysandre <lysandre@users.noreply.huggingface.co>e4c2dad
-
Build
a80ce84 -
Let git-lfs handle .so files
293c6ed -
Make repo a flake
64dd941 -
quant_weights is a CPU function
8294a79
-
Add README
f1c3798 -
Disable nvtx include
f5a110e -
Import EETQ kernels
1dc29e9