vLLM 第一时间给 Liquid AI 的 LFM2.5 小模型做了适配,230M 参数跑 agent 任务,手机、机器人上都能用。
vLLM 宣布 Day-0 支持 Liquid AI 的 LFM2.5-230M 小模型。该模型仅 230M 参数,预训练于 19T tokens 且支持 32K 上下文。专为手机、机器人、家庭自动化和网络设备上的 agent 任务设计。可运行于 CPU、NPU 和 GPU 等硬件。
🚀 Day-0 support for LFM2.5-230M on vLLM! Ready t…
🚀 Day-0 support for LFM2.5-230M on vLLM!
Ready to serve @liquidai's smallest LFM2 model for fast GPU inference and agentic workloads.
🧠 230M parameters, built on the LFM2 architecture 📚 Pre-trained on 19T tokens with 32K context 🛠️ Designed for agentic tasks across phones, robots, home automation, and network automation devices ⚡ Built to run across CPUs, NPUs, and GPUs
Congrats to the @liquidai team on the launch! Recipe: https://t.co/wGsn3B6JQf