Ciro Santilli @cirosantilli 37

This section discusses techniques that can be used to make LLMs infer with lower latency or greater throughput.

Bibliography:

There were still no amazing open source implementations as of 2025.

This section is about emulation setups that simulate both the microcontroller as well as the electronics it controls.

Bibliography:

People seeking QEMU-based solutions:

In discrete GPUs, VRAM is RAM memory that lives on the GPU's PCB.

They are located in separate chips to the GPU's compute, since just like for CPUs, you can't put both on the same chip as the manufacturing processes are different and incompatible.

Integrated GPUs don't have VRAM and just instead use the same RAM as the CPU.

Has some data, but appears less complete than WhoisXMLAPI at a quick glance.

Bibliography:

A "DNS database" is a database that stores DNS records, notably A-records, which IP a domains is hosted at.

For currently live domains, domain to IP can of course be easily determined on the fly by just resolving the domain like the browser does, e.g.

What is hard however is:

As of 2023, working with DNS data is just going through a mish-mash of closed datasets/expensive APIs.

We really need some open data in that area.

Some links of interest:

Bibliography:

In 2025 she disproved a conjecture and went to do a PhD before having finished high school.

Bibliography: www.quantamagazine.org/at-17-hannah-cairo-solved-a-major-math-mystery-20250801/

Bibliography: stackoverflow.com/questions/868568/what-do-the-terms-cpu-bound-and-i-o-bound-mean/33510470#33510470