Primary sourceLMSYS Org (SGLang)
View sourceEvent ·Multi-source
SGLang 推出低延迟模式,与 NVIDIA 和 AMD 合作开发
LMSYS 发布 SGLang 低延迟模式,与 NVIDIA 和 AMD 联合优化。在 SemiAnalysis 的 AgentX trace 回放中,DeepSeek-V4.1-Flash 配 DSpark 在 NVIDIA GB300 上 P90 单用户 token 速度提升 1.38 倍(671 到 928 tok/s),在 AMD MI355X 上提升 1.56 倍(332 到 516 tok/s)。技术细节上,NVIDIA 侧通过 kernel 重叠把 decoder 层时间从 96.8 µs 降到 68.4 µs,AMD 侧用每层 2 个 persistent kernel 替代几十个小 kernel。新插件系统支持外部库的自定义 kernel 接入并自动回退,GLM-5.3、K3 和 MiniMax M3 的低延迟 kernel 正在开发中。
Current read
SGLang 出了低延迟模式,在 GB300 和 MI355X 上跑 DeepSeek-V4.1-Flash 快了 1.38 到 1.56 倍,做推理部署的可以看看。
11 sources68° AI heatLast updated 2026/10/20 00:39:06
Evidence
11 sourcesRelated source 1berryxia
View sourceRelated source 2vLLM
View sourceRelated source 3SuperTechFans
View sourceRelated source 4shao__meng
View sourceRelated source 5Teortaxes
View sourceRelated source 6@atomic_chat_hq
View sourceRelated source 7marktechpost
View sourceRelated source 8Yuchen Jin
View sourceRelated source 9TestingCatalog
View sourceRelated source 10kimmonismus
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.