Local LLM projects, skills, and proof
Local LLM proof around self-hosted inference, model wrappers, prompt pipelines, queues, and operator review.
Related projects
2Local AI Model Gateway
Self-hosted LLM and diffusion workflow experiments around local inference, quantized models, API wrappers, prompt pipelines, queues, and human review boundaries.
Python, FastAPI, Docker, local LLMs, Qwen-style open-weight models, GGUF/quantized inference, SDXL-style diffusion workflows, API wrappers
Shows practical AI infrastructure work: running models locally, wrapping them into usable APIs, routing jobs through queues, and keeping operator approval around external actions.
GPU Orchestration Lab
Dockerized multi-stage GPU pipeline with Prefect and on-demand worker pools.
Docker, Prefect, RunPod, PostgreSQL, S3-compatible storage, FAISS, vLLM, FastAPI workers, Stable Diffusion, NLLB, CUDA
Shows orchestration separated from GPU-heavy stages so each workload can run in the right worker image and hardware profile.