MInference Background

MInference

Million-Tokens Prompt Inference for Long-context LLMs

News & features

Decorative graphic with wavy shapes in the background in blues and purples. Text overlay in center left reads: “Research Focus: August 26, 2024”
Microsoft Research Blog

Learn what’s next for AI at Research Forum on Sept. 3;  WizardArena simulates human-annotated chatbot games; MInference speeds pre-filling for long-context LLMs via dynamic sparse attention; Reef: Fast succinct non-interactive zero-knowledge regex proofs.