News for hackers. Stuff that matters.

A comment on Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s.

Re:Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,1... by maz1b on Friday October 25, 2024 @03:30AM (#41943037)
Cerebras really has impressed me with their technicality and their approach in the modern LLM era. I hope they do well, as I've heard they are en-route to IPO. It will be interesting to see if they can make a dent vs NVIDIA and other players in this space.
[ Parent | on HN ]
Re:Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,1... by madaxe_again on Friday October 25, 2024 @03:53AM (#41943174)
Apparently so. You can also buy in via various PE outfits before IPO, if you so desire. I did.
[ Parent | on HN ]
Re:Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,1... by Max-20 on Friday October 25, 2024 @07:52AM (#41944361)
Which one did you use? I am also interested to do that.
[ Parent | on HN ]