{"id":"2609.05764","title":"Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding","url":"https://codeofpaper.com/paper/2609.05764","arxiv_url":"https://arxiv.org/abs/2609.05764","published":"2026-09-04","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}