AMD MI355X vLLM HAS BEATEN B200 vLLM ON KIMI K2.5 (THE SAME MODEL ARCH AS XAI CU
Source
SemiAnalysis_
Author
SemiAnalysis_
Published
Why it matters
Upstream AMD inference beating Nvidia on a real model is the first hard evidence the CUDA gap is closing where it counts.
AMD MI355X vLLM HAS BEATEN B200 vLLM ON KIMI K2.5 (THE SAME MODEL ARCH AS XAI CURSOR COMPOSER 2.5)🚀🚨
This uses upstream AMD kernels from the @GPU_MODE community.
We explain below 👇 1/6🧵 https://t.co/98vEM7Z2vK
Transcript
AMD MI355X vLLM HAS BEATEN B200 vLLM ON KIMI K2.5 (THE SAME MODEL ARCH AS XAI CURSOR COMPOSER 2.5)🚀🚨
This uses upstream AMD kernels from the @GPU_MODE community. We explain below 👇 1/6🧵 https://t.co/98vEM7Z2vK
