[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Why do you think that https://github.com/ggerganov/whisper.cpp is a good alternative to streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Why do you think that https://github.com/ggerganov/whisper.cpp is a good alternative to streaming-llm