// TODO: I’m martinuke0
Welcome to my corner of the internet. This website is a personal blog which I use as a platform to document my learning journey and showcase it for the world to see.
Inside Apache Flink's Two-Phase Commit Sink: Exactly-Once Guarantees Across Sinks
How Apache Flink coordinates checkpoints with sink writers via a two-phase commit protocol to deliver end-to-end exactly-once guarantees across Kafka, filesystems, and databases.
Building a Paged KV Cache with GQA Sharing and Prefix-Reuse Eviction
TL;DR — A paged KV cache with grouped-query attention (GQA) sharing and a prefix-reuse eviction policy is one of the most credible LLM-systems projects you can ship to a CV in a weekend. It mirrors the design choices in vLLM, SGLang, and the RadixAttention paper, demonstrates that you understand memory hierarchies, attention math, and eviction, and produces a runnable artifact you can benchmark on real prompts. Why This Project Stands Out on a CV Hiring managers for inference, ML platform, and applied-LLM roles scan portfolios for evidence that a candidate can translate a paper into a working system. A paged KV cache hits that target harder than almost any other weekend project because the design space is genuinely contested in production: vLLM ships PagedAttention, SGLang ships RadixAttention, TensorRT-LLM ships in-flight batching with custom paged kernels, and HuggingFace TGI ships its own block manager. Building one from scratch proves you have read those systems and understood why they look the way they do. ...
Building a GGUF Parser and Tensor Loader From Scratch: A Portfolio Project That Actually Signals Systems Skill
Build a real GGUF parser and tensor loader from scratch in Rust — metadata parsing, q4_0/q8_0 dequantization, mmap’d weight streaming, and a minimal Llama forward pass. The kind of CV project that gets interviews at systems and ML infra teams.
Building a GGUF Weight Loader From Scratch: A CV-Grade ML Systems Project
Build a runnable GGUF parser and dequantizer for Q4_K and Q6_K, map the result into a PyTorch Llama model, and end up with a project that signals real ML systems skill on your CV.
Inside Cranelift: How a Baseline JIT Compiler Optimizes WebAssembly for Production Workloads
Cranelift is the baseline JIT that powers Wasmtime and Fastly’s edge platform. Here is how it compiles WebAssembly quickly, what optimizations matter at the baseline tier, and where it fits next to LLVM and TurboFan.