Sublime

An inspiration engine for ideas

Search

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

zack

GitHub - mit-han-lab/streaming-llm: Efficient Streaming Language Models with Attention Sinks

mit-han-lab github.com

Thumbnail of GitHub - mit-han-lab/streaming-llm: Efficient Streaming Language Models with Attention Sinks

Jesse Zhou - Business, Technology and Design

Thumbnail of Jesse Zhou - Business, Technology and Design

AgentBench: Evaluating LLMs as Agents

Xiao Liu • AgentBench: Evaluating LLMs as Agents

Lena Kul

Thumbnail of Lena Kul

In streaming settings, StreamingLLM outperforms the sliding window recomputation baseline by up to 22.2x speedup.

mit-han-lab • GitHub - mit-han-lab/streaming-llm: Efficient Streaming Language Models with Attention Sinks

L

Levi Lian

@levi

N

Neo Zhang

@neozhang