For those who have V100 cards, I wanted to point you to 1Cat-vLLM, a vLLM fork that enables optimized serving for these cards. Showing stats for Qwen3.6-35b comparing a Strix Halo with a hughly optimized llama.cpp fork (pwilkin) and the V100 with 1Cat. It’s not apples to apples, but I decided to sho
