Hands‑On Build Guide: Speculative Decoding Inference Engine in Pure Python
A step‑by‑step guide to building a speculative decoding inference engine in pure Python, showcasing draft and target transformer architectures for portfolio impact.
Cv-Project
Hands‑On: Building a Sampling & Decoding Demo for LLM Text Generation
A hands‑on project that implements LLM token‑sampling algorithms (temperature, top‑k, top‑p) with a CLI, tests and extensible architecture, perfect for demonstrating systems skills to hiring managers.
Hands-On GPTQ Quantization: A Portfolio Project That Signals Production Systems Skill
A step‑by‑step guide to building a GPTQ‑based quantization showcase that demonstrates low‑level systems expertise and impresses hiring managers.
From-Scratch Logits Processor and Sampler: Temperature, Top‑k, Top‑p, and Min‑p Decoding in Pure Python
A minimal, pure‑Python implementation of temperature‑scaled, top‑k, top‑p and min‑p token sampling, ready to run, test, and extend for your portfolio.
User Safety: A Hands‑On Build Guide for a Portfolio CV Project
A Go‑based CLI that validates and sanitises arbitrary user input against JSON schemas, logs every decision, and ships as a static binary for instant portfolio deployment.