https://moyutianzun.com/tags/mlsys24/Recent content in MLsys24 on moyutianzun 的博客Hugozh-cnmoyutianzunThu, 14 Aug 2025 15:51:24 +0800https://moyutianzun.com/blog/mlsys24-fen-lei-hui-zong/Thu, 14 Aug 2025 15:51:24 +0800https://moyutianzun.com/blog/mlsys24-fen-lei-hui-zong/<h1 style="" id="llm-%E6%8E%A8%E7%90%86%E4%B8%8E%E6%9C%8D%E5%8A%A1%E4%BC%98%E5%8C%96-(llm-inference-and-serving-optimization)"><strong>LLM 推理与服务优化 (LLM Inference and Serving Optimization)</strong></h1><p style=""></p><h2 style="" id="kv-%E7%BC%93%E5%AD%98%E7%AE%A1%E7%90%86%E5%92%8C%E4%BC%98%E5%8C%96-(kv-cache-management-and-optimization)"><strong>KV 缓存管理和优化 (KV Cache Management and Optimization)</strong></h2><p style=""></p><p style="">这些论文聚焦于 KV 缓存的减少、量化或重用，以提升生成推理效率和降低内存消耗。</p><ul><li><p style=""><a href="http://www.moyutianzun.cn/2025/07/30/keyformer%E9%98%85%E8%AF%BB%E7%AC%94%E8%AE%B0/">Keyformer: KV Cache reduction through key tokens selection for Efficient Generative Inference</a></p><ul><li><p style=""> (Keyformer：通过高效生成推理的关键令牌选择来减少 KV 缓存) - Muhammad Adnan 等</p>