Benchmarks de Inference Engines

https://dmatora.github.io/LLM-inference-speed-benchmarks/
https://twitter.com/ggerganov/status/1775921043858764061
https://twitter.com/ggerganov/status/1716737912929231346
https://twitter.com/ggerganov/status/1665403955801739267

Quitter le mode Zen