新闻
Announcing vllm-metal: Concurrent Serving on Apple Silicon
vLLM · Ranran Haoran Zhang, Lik Xun Yuan, Chao Ju Chen, Eric Curtin, Michael Goin · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- vLLM released vllm-metal v0.28.0, bringing concurrent LLM serving to Apple Silicon Macs with paged KV cache and OpenAI-compatible API.
- 为何重要
- Engineers running multiple overlapping inference requests on M1-M5 Macs need predictable latency, memory control, and batching beyond single-request inference.
- 注意
- Speculative decoding with MTP requires greedy sampling and synchronous scheduling; prefix caching for hybrid models remains experimental and incompatible with speculative decoding.
- agent
- llm
- serving
- vllm
这条新闻背后的模式
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。