发生了什么: SGLang and Miles Add Day-0 Support for Qwen3.8

SGLang and Miles added Day-0 support for Qwen3.8-2.4T-A95B, a 2.4 trillion parameter model with hybrid attention architecture.

为何重要: SGLang and Miles Add Day-0 Support for Qwen3.8

Matters for engineers deploying large language models at scale who need serving infrastructure optimized for complex hybrid architectures on launch day.

注意: SGLang and Miles Add Day-0 Support for Qwen3.8

The performance numbers are specific to GB300 GPUs with particular parallelism configurations; results may differ significantly on other hardware or setups.

新闻

SGLang and Miles Add Day-0 Support for Qwen3.8

LMSYS · 发布于 2026年8月12日 · 阅读约3分钟

30秒读懂

发生了什么: SGLang and Miles added Day-0 support for Qwen3.8-2.4T-A95B, a 2.4 trillion parameter model with hybrid attention architecture.
为何重要: Matters for engineers deploying large language models at scale who need serving infrastructure optimized for complex hybrid architectures on launch day.
注意: The performance numbers are specific to GB300 GPUs with particular parallelism configurations; results may differ significantly on other hardware or setups.

收听本摘要

阅读完整文章

qwen

这条新闻背后的模式

Infini-Attention Architecture
Hybrid Secret & Cache Management Pattern

每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。