Joe Barrow

Diffusion and speculative decoding both trade breadth for depth.

My attempt at a simple/visual explanation of arithmetic intensity and the roofline model, and why they matter for making LLMs go fast.

Inference Engineering by Philip Kiely is an excellent resource and if you think you need to read it, you probably need to read it.

Revisiting "Slow Search" in the age of agentic retrieval.

As a grad student, the one thing I desperately wanted was a GPU workstation.

Information retrieval is about satisfying an information need, but a query is a poor stand-in.

Strong, open VLMs enabled an explosion of open OCR model releases, with little sign of things letting up.

Probing the supported output types of Gemini.

Navigating Gemini's API for object detection with vision and Structured Outputs.

Thoughts on averaged benchmarks and hidden correlations.

The first post in the TinyHNSW series, introducing the tutorial and the library.