mit-han-lab/streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
License & maintenance
MIT is a permissive license: free to use commercially with attribution.
Last code push 2 years ago.
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
MIT is a permissive license: free to use commercially with attribution.
Last code push 2 years ago.