Kernels
attention
flash-attention
flash-attn-4
sm120
sm121
blackwell
rtx5090
rtx-pro-6000
dgx-spark
cute-dsl
Instructions to use vonkaiser/flash-attn-4-sm120 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use vonkaiser/flash-attn-4-sm120 with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("vonkaiser/flash-attn-4-sm120") - Notebooks
- Google Colab
- Kaggle
| { | |
| description = "Flake for flash-attn-4-sm120-sncbl (Dao-AILab/flash-attention SM120 PR bundle)"; | |
| inputs = { | |
| kernel-builder.url = "github:huggingface/kernels"; | |
| }; | |
| outputs = | |
| { | |
| self, | |
| kernel-builder, | |
| }: | |
| kernel-builder.lib.genKernelFlakeOutputs { | |
| inherit self; | |
| path = ./.; | |
| pythonCheckInputs = ps: [ ps.einops ]; | |
| }; | |
| } | |