Instructions to use replicate/flash-attn3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/flash-attn3 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-attn3", version=1) - Notebooks
- Google Colab
- Kaggle
Uploaded using `kernel-builder`.
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ This is the repository card of kernels-community/flash-attn3 that has been pushe
|
|
| 11 |
# make sure `kernels` is installed: `pip install -U kernels`
|
| 12 |
from kernels import get_kernel
|
| 13 |
|
| 14 |
-
kernel_module = get_kernel("kernels-community/flash-attn3")
|
| 15 |
flash_attn_combine = kernel_module.flash_attn_combine
|
| 16 |
|
| 17 |
flash_attn_combine(...)
|
|
@@ -27,4 +27,4 @@ flash_attn_combine(...)
|
|
| 27 |
|
| 28 |
## Benchmarks
|
| 29 |
|
| 30 |
-
Benchmarking script is available for this kernel. Run `kernels benchmark kernels-community/flash-attn3`.
|
|
|
|
| 11 |
# make sure `kernels` is installed: `pip install -U kernels`
|
| 12 |
from kernels import get_kernel
|
| 13 |
|
| 14 |
+
kernel_module = get_kernel("kernels-community/flash-attn3", version=1)
|
| 15 |
flash_attn_combine = kernel_module.flash_attn_combine
|
| 16 |
|
| 17 |
flash_attn_combine(...)
|
|
|
|
| 27 |
|
| 28 |
## Benchmarks
|
| 29 |
|
| 30 |
+
Benchmarking script is available for this kernel. Run `kernels benchmark kernels-community/flash-attn3 --version 1`.
|