Instructions to use replicate/paged-attention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/paged-attention 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/paged-attention", version=1) - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -10,3 +10,14 @@ tags:
|
|
| 10 |
|
| 11 |
Paged attention kernels from [vLLM](https://github.com/vllm-project/) and [mistral.rs](https://github.com/EricLBuehler/mistral.rs).
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
Paged attention kernels from [vLLM](https://github.com/vllm-project/) and [mistral.rs](https://github.com/EricLBuehler/mistral.rs).
|
| 12 |
|
| 13 |
+
|
| 14 |
+
### Performance
|
| 15 |
+
|
| 16 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_animation.svg" />
|
| 17 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_animation.svg" />
|
| 18 |
+
|
| 19 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_latency.svg" />
|
| 20 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_latency.svg" />
|
| 21 |
+
|
| 22 |
+
<img class="dark:hidden border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_light_throughput.svg" />
|
| 23 |
+
<img class="hidden dark:block border border-gray-200 dark:border-gray-700 rounded-lg" src="media/benches_dark_throughput.svg" />
|