Continuous batching from first principles

Unlocking asynchronicity in continuous batching

Putting ethical principles at the core of the research lifecycle

Training CodeParrot 🦜 from Scratch

Protecting people from harmful manipulation

Google DeepMind researches AI's harmful manipulation risks across areas like finance and health, leading to new safety measures.

From Files to Chunks: Improving HF Storage Efficiency

Letting Large Models Debate: The First Multilingual LLM Debate Competition