AITOPAI热报
general

SGLang Summit 2026 公布分会议程，聚焦模型与智能体训练系统

官方账号LMSYS Org (SGLang)@lmsysorg
Post
View the post
Why we picked it

SGLang Summit 在旧金山办了，议程讲怎么搭训练系统做智能体，做推理和训练的工程师可以看看。

LMSYS 公布了 SGLang Summit 2026 的部分分会场内容，主题集中在模型和智能体的训练系统搭建与扩展。会议定于 11 月 12 日至 13 日在旧金山 Fort Mason 举行。购买 expo 通行证即可参加分会场，更多议程将陆续公布。

Original · LMSYS Org (SGLang)

Check out the breakout sessions at SGLang Summit 2026 covering how teams build and scale training systems for models and agents!

📍 Nov 12–13 · Fort Mason, San Francisco Breakout access included with expo pass: https://t.co/gfxSV38bGY

Explore select sessions below 👇 More sessions to be announced

#SGLang#LMSYS#智能体

Keep reading

Recent stories with the same tag or section
ProductsBuildersSelected00:38
Alibaba Tair team co-leads SGLang agentic cache scheduling roadmap

KV cache reuse is becoming the bottleneck for agent serving, and engine-level cache sharing across parallelism setups is a practical lever for cutting latency and GPU cost. Teams running SGLang inference at scale can apply HiCache to avoid recomputing prefixes in multi-parallel, distributed deployments. Alibaba shaping an open-source inference stack also signals how Chinese cloud vendors compete at the serving layer.

#SGLang#Alibaba Cloud#Tair#HiCache
官方账号阿里云 Alibaba Cloud@alibaba_cloudSource