|
|
|
|
|
by karmasimida
504 days ago
|
|
Why? Serving is still a massive effort, requires massive amount of GPU memory to hold those models. I don't understand the logic that deepseek somehow is a blow to GPU demand. If anything, more people will try to build on top of R1 style model now, it is only going to drive demand, for customized training. |
|
DeepSeek has shown that you can achieve the same or better result on old hardware with less computing power.