←back to thread

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference

(cerebras.ai)
426 points benchmarkist | 1 comments | 19 Nov 24 00:15 UTC | HN request time: 0.211s | source
Show context
fillskills ◴[19 Nov 24 03:30 UTC] No.42179871[source]▶
No mention of their direct competitor Groq?
replies(2): >>42179927 #>>42180988 #
1. guyomes ◴[19 Nov 24 08:03 UTC] No.42180988[source]▶
Sambanova is not often mentioned either [0]. One of his co-founder is known as “father of the multi-core processor” [1].

[0]: https://sambanova.ai/

[1]: https://en.wikipedia.org/wiki/Kunle_Olukotun