Inferact says vLLM already performs well on Nvidia Vera Rubin and that more optimizations are on the way. The company points to current InferenceX results and a full breakdown on the vLLM blog.
Thanks for the shoutout @SemiAnalysis_! Our work at @inferact already has Vera Rubin performing well on @vllm_project, and we have more optimizations on the way.
Current results on InferenceX: https://inferencex.semianalysis.com/
Full breakdown on the vLLM blog: https://vllm.ai/blog/2026-10-09-vera-rubin-preview
ALERT🚨🚨: @vllm_project, @Inferact & NVIDIA TOOK CO-DESIGN TO THE EXTREME WITH A GB300 NVL72 INFERENCE OPTIMIZATION TO GET 🚀 7.2x 🚀 BETTER PERF PER TCO THAN LITERALLY EVERY OTHER AI CHIP, using an inference co-design optimization called wideEP take full advantage of the NVL72 BACKPLANE. We explain below👇️ (1/3)🧵
Source: Inferact · x.comPublished
