Mixtral 8x7B FP8 on H100 with Friendli Engine #shorts #mixtral #vllm

FriendliAI · Intermediate ·🧠 Large Language Models ·1y ago
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)
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Next Up
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)