Archive - Computer Science Research and Development

vLLM throughput-latency sweep on NVIDIA A100

Benchmarking Llama-3.1-8B-Instruct from one concurrent request to 64, and reading the result against the A100’s memory roofline.

May 25 • John Musgrave

March 2026

Pre-training an LLM base model (for under $20)

I was inspired by Andrej Karpathy’s Nanochat to train an LLM base model from scratch.

Mar 16 • John Musgrave

January 2026

Implementing a Transformer From Scratch

I wanted to analyze Andrej Karpathy’s NanoGPT implementation of the Transformer in detail.

Jan 5 • John Musgrave

July 2025

Support Vector Machine Classification of Data Dependency Graphs

I will be presenting this paper at the IEEE NAECON 2025 conference.

Jul 9, 2025 • John Musgrave

June 2024

kNN Classification of Malware Data Dependency Graph Features

I will be presenting this paper at the IEEE NAECON 2024 conference.

Jun 4, 2024 • John Musgrave

March 2024

Some recent papers

Search and Retrieval in Semantic-Structural Representations of Novel Malware

Mar 20, 2024 • John Musgrave

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts