arXiv:2405.14256 — ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

arXiv:2405.14256. v1 submitted 2024-05-23. Title on the /abs/ page confirmed as: "ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification". Venue/year for the corresponding paper record come from the Semantic Scholar graph API; see that record's notes where the arXiv comment field or OpenReview was used instead.