The Inference Engineering Masterclass: 10x faster models, quantization, speculative decoding, Rubin, & self-optimizing AI https://www.latent…

The Inference Engineering Masterclass: 10x faster models, quantization, speculative decoding, Rubin, & self-optimizing AI https://www.latent.space/p/inference-eng @Baseten @philipkiely and @waterloo_intern explain what actually happens after a model is trained, why turning weights into a fast and reliable product creates an entirely new optimization problem, how quantization errors can cancel out to unlock more throughput, why inference teams are still finding 20–200% performance gains, how video generation runs into a quadratic attention wall, and how GLM-5.2 helped rewrite and optimize the GPU kernels serving GLM-5.2 itself. Media

Source: Swyx (X) | 2026-08-03