Yesterday I said Jev would open a ton of doors...
24 hours later, this exists.
Cua built a 2.8MB model that scored 99.7% on their form-filling eval.
Hosted Jev scored 83.6%.
Not to mention it's FREE and only 706K parameters.
Small enough to run locally with not even 1gb or ram.
Fast enough to make decisions in one pass.
And specialized enough that your agent doesn't need to call a giant LLM for every tiny action.
Think about what this unlocks.
Every repetitive computer task could eventually get its own tiny specialist:
• forms
• CRM updates
• data entry
• browser actions
• document routing
• UI decisions
Then one powerful agent just routes work between them.
We are going to see some ridiculous stuff built from this as well.
Remember when Mia Khalifa stepped into a wrestling ring and realized how tough pro wrestling actually is after previously calling it “fake” and showing no respect for it?
大模型推理加速技术的学习路线是什么?
推荐直接看 CMU 陈天奇大佬最新的推理综述:
Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems
https://t.co/TY0OyKWSdp