Loading repository and market data…
Loading repository and market data…
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
This repository is available to tokenize. Be the first known launch in Gitpad’s index.
Tokenize this repoNo verified token is indexed. This is not a claim of global uniqueness.Contributors are shown as project information, not fee recipients. GitHub repository ID: 663368311.
Paste the contract to inspect real onchain data. Saved on this browser only; repository association and creator fees remain unverified.