PRs: #9225 #9232
The setup was modest. Two RTX 4090s in my basement ML rig, running quantised models through ExLlamaV2 to squeeze 72-billion parameter models into consumer VRAM. The beauty of this method is that you don’t need to train anything. You just need to run inference. And inference on quantized models is something consumer GPUs handle surprisingly well. If a model fits in VRAM, I found my 4090’s were often ballpark-equivalent to H100s.
，更多细节参见新收录的资料
所以，董红光并不认为「光帆科技」仅仅只是一个AI耳机公司，而是一个以操作系统为主、软硬结合的公司。，这一点在新收录的资料中也有详细论述
Now scientists who track the animals using satellite pictures can no longer find most of the birds. They fear that thousands of penguins may have frozen in Antarctica's icy waters.，更多细节参见新收录的资料