Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
Paper
•
2403.09636
•
Published
•
2
Inference
-
-
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
Paper • 2404.11912 • Published • 16 -
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Paper • 2401.02669 • Published • 14 -
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 73 -
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
Paper • 2404.18911 • Published • 29 -
Octopus v4: Graph of language models
Paper • 2404.19296 • Published • 117 -
Better & Faster Large Language Models via Multi-token Prediction
Paper • 2404.19737 • Published • 73 -
Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
Paper • 2405.19893 • Published • 29 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 28 -
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Paper • 2406.15319 • Published • 61 -
Writing in the Margins: Better Inference Pattern for Long Context Retrieval
Paper • 2408.14906 • Published • 138