Dao-AILab/flash-attention
fast attention algorithm for transformers, boosts speed and memory efficiency
View on index · View in 3D Map
Related repos
- Sparse attention for long video generation
- Efficient Triton-based linear attention kernels for PyTorch and multiple hardware platforms
- Nanotron: minimalistic library for pretraining transformer models with simple API and scalable parallelism
- Memory system for AI assistants
- Diffusion transformer for image generation with sub-second latency
- transformers library for working with machine learning models
- Memory system for AI agents
- Generative pre-trained transformers for time series analysis
- Extension of Transformers for optimizing and running models on specific hardware
- Next.js SaaS platform for AI video generation
