AMD’s data center Instinct MI300X GPU can compete against Nvidia’s H100 in AI workloads, and the company has finally posted an official result for MLPerf 4.1 — for the Llama 2 70B LLM at least. It’s roughly in line with the H100 but noticeably slower than H200 and B200.
AMD’s data center Instinct MI300X GPU can compete against Nvidia’s H100 in AI workloads, and the company has finally posted an official result for MLPerf 4.1 — for the Llama 2 70B LLM at least. It’s roughly in line with the H100 but noticeably slower than H200 and B200.