Red Hat CTOs on inference-time scaling connected with reasoning capabilities

Red Hat CTO Chris Wright and AI CTO Brian Stevens talk about the importance of inference and optimization. “Now all the sudden, we’re building these models that build all these intermediate-state tokens that’s producing far more tokens than what you’ll ever see… You better be as hyper efficient as possible.”

Watch the full episode of Technically Speaking with Chris Wright on YouTube.

#AI #redhat #llm #distributedinference