Instructions to use kernels-community/flash-attn2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use kernels-community/flash-attn2 with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("kernels-community/flash-attn2") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -147,3 +147,14 @@ Reference variable length output: torch.Size([10, 4, 8])
|
|
| 147 |
Outputs close: True
|
| 148 |
```
|
| 149 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
Outputs close: True
|
| 148 |
```
|
| 149 |
|
| 150 |
+
|
| 151 |
+
### Performance
|
| 152 |
+
|
| 153 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_animation.svg" />
|
| 154 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_animation.svg" />
|
| 155 |
+
|
| 156 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_latency.svg" />
|
| 157 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_latency.svg" />
|
| 158 |
+
|
| 159 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_throughput.svg" />
|
| 160 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_throughput.svg" />
|