Research
Quantisation, inference economics and the evidence behind the engineering decisions.
LLM quantisation for edge GPUs
MSc, Machine Learning - American University of Sharjah · 2024 – expected 2027
Post-training quantisation of open-weight language models, benchmarked across both NVIDIA and AMD accelerators: throughput, memory footprint, accuracy retention per method, and the cost-per-token implication of each. Cross-vendor comparisons are scarce because few people have both estates, which is the whole reason it is worth doing.
Code and benchmarks: llm-quant-lab
Publications
- Post-training quantisation of large language models across NVIDIA and AMD accelerators
- Malicious URL and Intrusion Detection using Machine Learning
- Understanding Diabetes Distress: A Machine Learning Approach