Instructions to use replicate/activation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/activation 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/activation", version=1) - Notebooks
- Google Colab
- Kaggle
Commit History
-
Build (aarch64)
fd15df4 -
Build
22de15a -
Update flake
4b773b6
-
Build (with ROCm)
d362e14 -
Add flake.lock
1c2cb8f -
Enable ROCm in the build
02452f1
-
feat: update to include rev in kernel for reproducible symbols (#2)
Unverified signature- feat: update to include rev in kernel for reproducible symbols (5d099145740601e9f102c355edfbab30ba7b061c)7dc5871 -
Fix kernel-builder URL
29b4fa8
-
Add layers
e21f2b2
-
Update README.md (#1)
Unverified signature- Update README.md (b0b50a4a8e0dbd916ceb15503e1252dcaaf0e663) Co-authored-by: Lysandre <lysandre@users.noreply.huggingface.co>e428458 -
Update for build.toml changes
e09b337
-
Torch 2.6 build
7c616ae
-
Build (op name with randomness example)
a0b0bfd
-
Build
5140606 -
Update for kernel-builder changes
badcb1a
-
Build
f0d0ac3 -
Fix a couple of bugs and add tests from vLLM
a4b03f4 -
Use new flake generation
5f7ed6e -
Make this a repo a flake for convenience
3ea02dc
-
Build
e83247b -
Use git-lfs to handle .so files
028a5e6
-
Update for new Python source specification
f550b40
-
Add Torch as an explicit dependency
This is require starting with kernel-builder 0.0.3.adb784a -
Add extension versioning
dee1261
-
Add build
Unverified signatureaf4a488 -
Add activation kernels
Unverified signature703f177 -
initial commit
Unverified signatureb808e08