optimizing-attention-flash - AI Research Skills
by Orchestra Research
Cross-platformSkillskillai-researchAI-Research-SKILLs-main
Description
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.
Type
Skill
Ecosystem
Cross-platform
Trust Score
85%
Related Skills
Stable Diffusion WebUI
Feature-rich web interface for Stable Diffusion image generation by AUTOMATIC1111.
Cross-platformai-tool
LangChain
Comprehensive framework for building LLM-powered applications with chains, agents, and retrieval.
Cross-platformframework
LobeChat
Modern, extensible AI chat framework with plugin ecosystem and multi-model support.
Cross-platformopen-source
Open WebUI
Self-hosted web UI for LLMs with multi-model support, RAG, and plugin system.
Cross-platformopen-source