DeepSeek Ultrafast

(github.com)

11 points | by neo2006 5 hours ago ago

2 comments

  • platinumrad 5 hours ago ago

    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.

  • rvz 4 hours ago ago

    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