Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -12,3 +12,14 @@ rotary embedding kernel from [Flash Attention](https://github.com/Dao-AILab/flas
|
|
| 12 |
|
| 13 |
Kernel source: https://github.com/huggingface/kernels-community/tree/main/rotary
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
Kernel source: https://github.com/huggingface/kernels-community/tree/main/rotary
|
| 14 |
|
| 15 |
+
|
| 16 |
+
### Performance
|
| 17 |
+
|
| 18 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_animation.svg" />
|
| 19 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_animation.svg" />
|
| 20 |
+
|
| 21 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_latency.svg" />
|
| 22 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_latency.svg" />
|
| 23 |
+
|
| 24 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_throughput.svg" />
|
| 25 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_throughput.svg" />
|