domains / families / data / flash-attention

flash-attention

separate

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.

When to use

• Training transformers with sequences >512 tokens
• Running inference with long context (>2K tokens)
• GPU memory constrained (OOM with standard attention)
• Need 2-4x speedup without accuracy loss
• Using PyTorch 2.2+ or can install flash-attn
• **Standard attention**: Sequences <256 tokens (overhead not worth it)
• **xFormers**: Need more attention variants (not just speed)
• **Memory-efficient attention**: CPU inference (Flash Attention needs GPU)

Skill page

Source