According to the official vLLM blog, the throughput increase of Rubin over GB300 is 58×, based on a rack-to-rack comparison using the AgentX workload at 387 tokens per second per user.
Source:explainx.ai · Read Original
According to the official vLLM blog, the throughput increase of Rubin over GB300 is 58×, based on a rack-to-rack comparison using the AgentX workload at 387 tokens per second per user.
Source:explainx.ai · Read Original
Leave a Reply