Paper Reviews
Section-by-section dissections of research papers and engineering posts: the math worked through, and where I agree or push back. Each review reads beside its source, which follows along as you scroll.
- vLLM Blog · Martin Hickey (IBM Research), 2026 Blog review Prefill, Decode, and the Quiet Third Job: Reviewing vLLM's Guide to Disaggregated Serving Why long prompts make every stream stutter, when splitting prefill from decode pays off, and why tokenization belongs off the GPU, with a first-principles simulator that reproduces the guide's benchmark.
- Context Language Models · Shao, Shen, Yin, et al., 2026 Context Language Models, Dissected: Letting the Model Edit Its Own Context, the Math Behind It, and Where I Disagree A section-by-section review of Context Language Models (Shao et al., 2026): the formalism, prefix-reuse FLOPs, stepwise GRPO with a success-gated efficiency advantage, and Suffix Cache Reuse, with refreshers along the way.