Dragonfly: A large vision-language model with multi-resolution zoom(together.ai)131 points by jasondavies 2 years ago | 32 comments
AdapTive-LeArning Speculator System (ATLAS): Faster LLM inference(together.ai)192 points by alecco 1 year ago | 43 comments
Based: Simple linear attention language models(together.ai)143 points by swyx 2 years ago | 11 comments
Consistency diffusion language models: Up to 14x faster, no quality loss(together.ai)203 points by zagwdt 8 months ago | 91 comments
FlexAttention: The Flexibility of PyTorch with the Performance of FlashAttention(pytorch.org)194 points by limoce 2 years ago | 21 comments
FlashAttention: Fast Transformer training with long sequences(adept.ai)140 points by kristianp 3 years ago | 8 comments
