Consistency diffusion language models: Up to 14x faster, no quality loss(together.ai)203 points by zagwdt 8 months ago | 91 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
A practitioner's guide to testing and running GPU clusters(together.ai)75 points by nutlope 2 years ago | 8 comments
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-Precision(together.ai)269 points by jhshah 2 years ago | 53 comments
DeepCoder: An Open-Source 14B Coder at O3-Mini Level(together.ai)7 points by tosh 1 year ago | 1 comments
