What it does
This skill optimizes transformer attention with Flash Attention. It supports PyTorch native SDPA, the flash-attn library, H100 FP8 and sliding window attention. The publisher describes speedups of 2-4x and memory reduction of 10-20x.
It is suited to training or running transformers on sequences longer than 512 tokens, to cases where attention causes GPU memory problems, and to situations where faster inference is needed.
The publisher's description does not specify installation or setup steps. The skill is released under the MIT license.
Limitations and requirements
FP8 support is listed for H100 GPUs only. The publisher's description does not state other requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 39
optimization-flash-attention
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
v1.0.0As shown on www.aitmpl.com when we last read it