Luca Lowndes blog

AI models don't know what they want to say.

I'm going to try writing up one thing I've optimised/done atleast once a week.

Hello LinkedIn Fam, welcome to Optimisations Wednesday.

My paper "Less is More: Optimising SGLang Distributed DeepSeek-R1 Inference on a Two-Node H200 Cluster" has been accepted for presentation at the BID Workshop at ICPP 2026, the International Conference on Parallel Processing.

Posted by Monash Engineering on LinkedIn.

Notes from the NSCC Singapore ASPIRE-2A+ supercomputer, written during the 8th APAC HPC-AI Competition while benchmarking DeepSeek-R1 inference on SGLang.

Notes from Monash University's M3 supercomputer.

Notes from running DeepSeek-R1 inference on SGLang during the 8th APAC HPC-AI Competition.

These are the notes I actually use, the flags, the couplings, and the reasoning behind every knob we turned on DeepSeek-R1 during the 8th APAC HPC-AI Competition.

I joined the Neural Cellular Automata team at Monash DeepNeuron in February 2025.

I trained an MNIST classifier and got 98% on the test set, which tells you how it does on other people's handwriting.