Mixtral 8x7B FP8 on H100 with Friendli Engine #shorts #mixtral #vllm
Mixtral 8x7B FP8 is action on Friendli Engine! Friendli Engine runs blazingly fast compared to vLLM.
* Under the same load condition, we send the same generation request to each engine.
#shorts #vllm #mixtral
Watch on YouTube ↗
(saves to browser)
DeepCamp AI