Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -30,3 +30,14 @@ convert_fp8(...)
|
|
| 30 |
## Benchmarks
|
| 31 |
|
| 32 |
Benchmarking script is available for this kernel. Run `kernels benchmark kernels-community/paged-attention`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Benchmarks
|
| 31 |
|
| 32 |
Benchmarking script is available for this kernel. Run `kernels benchmark kernels-community/paged-attention`.
|
| 33 |
+
|
| 34 |
+
### Performance
|
| 35 |
+
|
| 36 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_animation.svg" />
|
| 37 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_animation.svg" />
|
| 38 |
+
|
| 39 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_latency.svg" />
|
| 40 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_latency.svg" />
|
| 41 |
+
|
| 42 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_throughput.svg" />
|
| 43 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_throughput.svg" />
|