Tag gpu 4 posts Inference Engineering - Part 6: Diffusion, and What Ties It Together Oct 2, 2026 Inference Engineering - Part 5: Sampling, From the API Down to the Bits Oct 2, 2026 Inference Engineering - Part 4: It's Memory Bandwidth All the Way Down Oct 1, 2026 Inference Engineering - Part 2: What Actually Runs the Model Sep 27, 2026