LMDeploy v0.17.0 发布：集成 DeepEPv2 并支持 Kimi K2.6

AI 摘要

LMDeploy 发布 v0.17.0 版本，集成了 DeepEPv2，支持 Kimi K2.6 和 mooncake store，并优化了 GLM-5.2 服务性能。该版本还引入了服务端 fan-out、PDL 分页注意力、FP8 MoE 优化等改进，并修复了多个 bug。

正文节选

<!-- Release notes generated using configuration in .github/release.yml at main --> ## What's Changed ### 🚀 Features * Integrate DeepEPv2 by @irexyc in https://github.com/InternLM/lmdeploy/pull/4783 * feat(pytorch): support Kimi K2.6 by @qescccczmr in https://github.com/InternLM/lmdeploy/pull/4846 * feat(kv_connector): support mooncake store by @caikun-pjlab in https://github.com/InternLM/lmdeploy/pull/4903 ### 💥 Improvements * feat(chat-completions): server-side fan-out for n>1 choice

发布时间：2026-09-01 15:13

抓取时间：2026-09-01 16:15

来源机构：Shanghai AI Laboratory