Instructions to use replicate/flash-attn4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/flash-attn4 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/flash-attn4", version=1) - Notebooks
- Google Colab
- Kaggle
Download build/torch-cuda/metadata.json from replicate/flash-attn4: direct link, hf CLI and curl.
- Browser
- Download file 128 Bytes
-
https://huggingface.co/replicate/flash-attn4/resolve/main/build/torch-cuda/metadata.json
- Command line
-
hf download hf://replicate/flash-attn4/build/torch-cuda/metadata.json
-
curl -L -o metadata.json https://huggingface.co/replicate/flash-attn4/resolve/main/build/torch-cuda/metadata.json
128 Bytes
| { | |
| "version": 0, | |
| "license": "BSD-3-Clause", | |
| "python-depends": [ | |
| "einops", | |
| "tvm-ffi", | |
| "nvidia-cutlass-dsl" | |
| ] | |
| } |