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 folder using huggingface_hub
Browse files- media/benches_dark_animation.svg +18 -18
- media/benches_dark_latency.svg +349 -313
- media/benches_dark_throughput.svg +283 -247
- media/benches_light_animation.svg +18 -18
- media/benches_light_latency.svg +349 -313
- media/benches_light_throughput.svg +283 -247
media/benches_dark_animation.svg
CHANGED
|
|
|
|
media/benches_dark_latency.svg
CHANGED
|
|
|
|
media/benches_dark_throughput.svg
CHANGED
|
|
|
|
media/benches_light_animation.svg
CHANGED
|
|
|
|
media/benches_light_latency.svg
CHANGED
|
|
|
|
media/benches_light_throughput.svg
CHANGED
|
|
|
|