作为 SGLang 核心维护方,RadixArk 在 SGLang Summit 2026 上公布了 SGLang v1.0、Miles v0.2 以及由 NVIDIA、AMD、Intel、Google、Meta、Thinking Machines Lab 等九家创始成员组成的 SGLang Consortium。
Big updates from SGLang x RadixArk at SGLang Summit 2026!
As a core maintainer of SGLang, RadixArk is driving several interesting developments across AI inference and RL infrastructure:
SGLang Consortium — 9 founding members, including NVIDIA, AMD, Intel, Google, Meta, Thinking Machines Lab, and RadixArk, joining forces to advance open-source inference
SGLang v1.0 — A major milestone focused on production reliability across scheduling, caching, and distributed serving
SGLang on AWS Trainium — RadixArk and AWS Annapurna Labs bring LLM serving and RL rollouts to Trainium through SGLang-Neuron
RadixArk x Intel — Collaborating to optimize SGLang inference across Intel CPUs, GPUs, and accelerators
Miles v0.2 by RadixArk — Expanding heterogeneous hardware support, fully asynchronous RL, and multimodal training
From high-performance inference to scalable RL training, SGLang and RadixArk are making open AI infrastructure more accessible and efficient.
Exciting progress for the open-source AI ecosystem!
2,000+ people. Two days. The first SGLang Summit. Together, we announced SGLang v1.0, released Miles v0.2, and launched the SGLang Consortium with nine founding members: @nvidia, @AMD, @intel, @Google, @Meta, @thinkymachines, @Cloudflare, @modal, and @radixark. SGLang is now used by 332 organizations. At Meta, it powers production inference for products serving billions of users. Teams from Modal, Cloudflare, LinkedIn, and others shared their production lessons. Across 90+ technical talks and six hands-on workshops, the community explored what comes next for inference, reinforcement learning, and AI agents. To everyone building, deploying, and contributing: thank you for making this possible. Explore the announcements, engineering lessons, and moments from SGLang Summit 2026 in the link below.在 X 查看被引用的帖子
来源:Dongxi 东锡 NLP · x.com