← authors · overview

• Longllmlingua: Accelerating And Enhancing Llms In Long Context Scenarios Via Prompt Compression
  2023 · 407 citations
• Minference 1.0: Accelerating Pre-filling For Long-context Llms Via Dynamic Sparse Attention
  2024 · 309 citations
• Llmlingua-2: Data Distillation For Efficient And Faithful Task-agnostic Prompt Compression
  2024 · 254 citations
• Llmlingua: Compressing Prompts For Accelerated Inference Of Large Language Models
  2023 · 227 citations
• Parrot: Efficient Serving Of Llm-based Applications With Semantic Variable
  2024 · 105 citations