新闻
Inkling 2 Mini on vLLM: Day-0 Support for a Looped Model
vLLM · Inferact, Thinking Machines and NVIDIA · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- vLLM added day-0 support for Inkling 2 Mini, a looped multimodal model with 26B total and 3.5B active parameters running on NVIDIA hardware.
- 为何重要
- Engineers deploying or evaluating Inkling 2 Mini need this support to serve the model efficiently with its variable-loop research checkpoint option.
- 注意
- The looped architecture requires 48 separate KV caches instead of 24, and DSpark speculative decoding requires the default three-pass configuration.
- llm
- speculative
- kernel
- kv cache
- 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。