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.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/nousresearch/hermes-agent/main/optional-skills/mlops/flash-attention/SKILL.mdRegistry
github (via claudemarketplaces.com)