Monday 19 February 2024

Groq runs Mixtral 8x7B-32k with 500 T/s

Groq runs Mixtral 8x7B-32k with 500 T/s
531 by tin7in | 361 comments


-
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy 379 by weinzierl | 72 comments