https://akeelmedina22.github.io/tags/llms/Recent content in LLMs on Akeel Ather MedinaHugoen-usWed, 06 Aug 2025 00:00:00 +0000https://akeelmedina22.github.io/posts/2026-05/Wed, 06 Aug 2025 00:00:00 +0000https://akeelmedina22.github.io/posts/2026-05/<p>As a participant representing TeamEPCC in the ISC Student Cluster Competition 2026, I&rsquo;ve recently had the chance to work on a custom-built HPC cluster, to be shipped to Hamburg for the in-person competition. Until then, I have to keep cluster specs and optimization efforts secret, but I wanted to give my thoughts on a specific topic: can you optimize an application without fully understanding it?</p> <p>The competition itself has never included Llama.cpp as a micro-benchmark, usually focusing on HPC-specific benchmarks like HPL and HPCG. This year introduced Llama.cpp, which allows LLM inference with minimal setup on a wide range of hardware. It is a plain C/C++ implementation with no dependencies. It runs surprisingly well on Apple silicon as well! Understanding Llama.cpp is fairly simple. Maximizing performance is whole other thesis. While the source code is very well written, and it is easy to find and read specific implementations of custom kernels, the majority of performance comes from tuning the runtime parameters, understanding the workload and how these parameters alter the characteristics of your problem on your given hardware. While I have to stay a bit vague, I believe this problem is somewhat unique from the other application benchmarks, like HPL.</p>