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.
no risky patterns detected
Type: Agent skill (SKILL.md) · Category: Memory & Knowledge · Source: https://github.com/dabit3/sonic-agent/tree/HEAD/optional-skills/mlops/flash-atte
| Capabilities (fewer powerful permissions = higher) | 50/50 |
| Maintenance | 26/35 |
| Documentation | 15/15 |
Always review files before installing. How scores work. Request a correction