DeepSeek Ultrafast

This will be very useful to me as someone who still uses LLMs interactively rather than trusting the harness to one-shot the whole thing.

I'll just go get my 8 x B300 (TP8) from the shed and start this up real quick

Please continue. [0] Let's see what happens when it goes even faster than 2,400 TPS and why not host an abliterated version of this model as well.

What could possibly go wrong?

[0] https://news.ycombinator.com/item?id=50310886