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.
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs/plugin install optimizing-attention-flash@zechenzhangAGI/AI-research-SKILLs