LMSYS成立SGLang联盟：英伟达与AMD等8家创始成员、首届峰会11月12日至13日在旧金山举行
非营利组织LMSYS Org于2026年11月12日宣布成立SGLang Consortium联盟，创始成员为英伟达、AMD、英特尔、谷歌、Meta、Cloudflare、Modal与RadixArk共8家，将与开源推理引擎SGLang的维护者共同规划项目路线图，推进开源超级智能推理。联盟在旧金山举行的首届SGLang Summit开幕主旨演讲中宣布，峰会于11月12日至13日在Fort Mason Center for Arts & Culture举行，100多名来自超级智能硬件、模型、基础设施与应用领域的演讲者参加。
LMSYS引用德勤的估计称，推理预计约占2026年全部超级智能算力的三分之二，高于2025年的约一半。SGLang是面向前沿超级智能的全栈推理引擎，属PyTorch生态，运行于数十万块GPU之上，支撑着Meta、微软、谷歌、亚马逊等公司的大规模生产推理部署。
联盟为成员设常设论坛，与维护者讨论新兴推理趋势，并把共同优先事项转为联合工程工作，重点包括前沿模型支持、推理与多模态负载、分布式推理与硬件优化。每家创始成员将指定一名技术代表，每年参加两次路线图会议，并以工程专长、部署反馈、测试资源或联合开发等方式参与。SGLang维护者保留技术决策与代码接受的责任，项目继续向整个社区开放。英伟达负责超大规模与高性能计算的副总裁Ian Buck表示，英伟达很自豪成为创始成员，并与社区共同推进开放推理软件。
（来源：LMSYS）
LMSYS Launches the SGLang Consortium With Eight Founding Members Including NVIDIA and AMD: The First SGLang Summit Runs November 12 to 13 in San Francisco
LMSYS Org, the nonprofit behind the open-source AI engine SGLang, announced on November 12, 2026, the launch of the SGLang Consortium, with founding members NVIDIA, AMD, Intel, Google, Meta, Cloudflare, Modal and RadixArk, who will work with SGLang's maintainers to help shape the project's roadmap and advance open-source AI inference. The consortium was announced in the opening keynote of the inaugural SGLang Summit, held November 12 to 13 at the Fort Mason Center for Arts & Culture in San Francisco, with more than 100 speakers from across AI hardware, models, infrastructure and applications taking part. Citing Deloitte, LMSYS said inference is expected to account for roughly two-thirds of all AI compute in 2026, up from about half in 2025. SGLang, the full-stack inference engine for frontier AI and part of the PyTorch ecosystem, runs on hundreds of thousands of GPUs and powers large production inference deployments for companies including Meta, Microsoft, Google, Amazon, Thinking Machines Lab, Cloudflare, Reflection and Modal. The consortium gives members a standing forum to discuss emerging inference trends with SGLang's maintainers and turn shared priorities into joint engineering work, focused on frontier model support, reasoning and multimodal workloads, distributed inference and hardware optimization. Each founding member will designate a technical representative and join two roadmap meetings a year, contributing engineering expertise, deployment feedback, testing resources or joint development, while SGLang's maintainers keep responsibility for technical decisions and code acceptance and the project stays open to the entire community. Ian Buck, NVIDIA's vice president of hyperscale and high-performance computing, said NVIDIA is proud to be a founding member and to work with the community to advance open inference software.
(Source: LMSYS Org)
来源：LMSYS
发布：GSM·美国（发布链接）
图片来源：图：数据中心机房内的服务器机柜。123net，CC BY-SA 3.0，经 Wikimedia Commons。 / Photo: 123net, CC BY-SA 3.0, via Wikimedia Commons.
GSM Global · 本篇英文版 English edition of this story
