https://harsha-moparthy.github.io/MVS Sri Harsha — machine learning engineer. LLM inference and serving, agent reliability, and AI systems security, with measured results. 2026-07-31T16:19:39+05:30 MVS Sri Harsha https://harsha-moparthy.github.io/ Jekyll © 2026 MVS Sri Harsha /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png 2026-07-30T13:00:00+05:30 2026-07-30T13:00:00+05:30 https://harsha-moparthy.github.io/posts/high-information-blogroll/ MVS Sri Harsha

The writers whose archives are worth reading end to end: Ciechanowski's interactive essays, Dan Luu, rachelbythebay, Bert Hubert, Fabien Sanglard, and the rest of the highest signal-per-post writers on the internet.

2026-07-30T12:30:00+05:30 2026-07-30T12:30:00+05:30 https://harsha-moparthy.github.io/posts/math-goldmines/ MVS Sri Harsha

The freely available math that punches far above its fame: Evan Chen's Napkin, MIT's Mathematics for CS, Linear Algebra Done Wrong, and the Boneh–Shoup cryptography book with cryptopals as its gym.

2026-07-30T12:00:00+05:30 2026-07-30T12:00:00+05:30 https://harsha-moparthy.github.io/posts/gpu-ml-performance-goldmines/ MVS Sri Harsha

Where the GPU-performance knowledge actually lives: PMPP, GPU MODE, Simon Boehm's matmul worklog, Horace He's brrrr essay, the Ultra-Scale Playbook, and Stas Bekman's open ML-engineering book.

2026-07-30T11:30:00+05:30 2026-07-30T11:30:00+05:30 https://harsha-moparthy.github.io/posts/compilers-goldmines/ MVS Sri Harsha

The language-implementation canon that actually gets read: Crafting Interpreters, Russ Cox's essays, Eli Bendersky's archive, matklad, and the Architecture of Open Source Applications.

2026-07-30T11:00:00+05:30 2026-07-30T11:00:00+05:30 https://harsha-moparthy.github.io/posts/database-goldmines/ MVS Sri Harsha

The database-internals material practitioners actually learn from: Use The Index Luke, CMU 15-445/721, Database Internals, the Red Book, and the blogs where people build storage engines in public.