行业58

Cerebras发布了一条内容

Cerebras@cerebras发布时间 (北京时间)

https://x.com/seanlie/status/2123129836277551288?a=PKJ-D11bHK2xd6Om0YQ&s=20

中文译文尚未完成,先为你展示原文。

The first model we ever served at @cerebras was Llama 70B at 450 tokens/sec. That was just over two years ago. Now we’re serving Kimi K3.1 Pro, a 2.8 trillion parameter model, at up to 2,000 tokens/sec. It has 40x the parameters, and our inference speeds are only going up. I’m extremely proud of how far we’ve come, but also that we’ve stayed committed to the open model community along the way. We want developers to have more models to choose from and the speed to actually build with them.
查看原帖
推理能力部署工程行业动态#行业动态#推理#部署/工程