Re:Groq runs Mixtral 8x7B-32k with 500 T/s
by deepnotderp on Monday February 19, 2024 @12:55PM
(#39432648)
This demo has more than 500 chips btw, it’s not exactly an apples to apples comparison with 1 GPU…
[ Parent
| on HN ]
Definitely not, but even with a comparison to 500 GPUs Groq will still come out on top because you can never reduce latency by adding more parallel compute :)
Re:Groq runs Mixtral 8x7B-32k with 500 T/s
by varunvummadi on Monday February 19, 2024 @02:42PM
(#39433818)
So please let me know if I am wrong are you guys running a batch size of 1 in 500 GPU's? then why are the responses almost instant if you guys are using batch size 1 and also when can we expect bring your own fine tuned models kind of thing. Thanks!
We are not using 500 GPUs, we are using a large system built from many of our own custom ASICs. This allows us to do batch size 1 with no reduction in overall throughput. (We are doing pipelining though, so many users are using the same system at once).
Re:Groq runs Mixtral 8x7B-32k with 500 T/s
by deepnotderp on Sunday February 25, 2024 @12:55PM
(#39503007)
> GPUs Groq will still come out on top because you can never reduce latency by adding more parallel compute :)
You literally can, in fact that’s the entire reason to use multiple chips.
See eg the TPU group’s paper: https://arxiv.org/abs/2211.05102