Run AI without a GPU? 🤯💻

Remember waiting for a single webpage to load line-by-line over a 14.4K dial-up modem back in 1995? While early CPU inference was painfully slow, next-gen x86 architecture is changing the paradigm. Go inside the engineering behind this shift to learn how to evaluate your infrastructure, calculate inter-token latency benchmarks, and unlock massive deployment flexibility. #CPUInference #AIInfrastructure #redhat

🎧 Listen to the new episode now wherever you get your podcasts