AI/ML

A detailed vLLM blog post explaining speculative decoding on AMD GPUs, with mechanics, supported drafting methods, configuration guidance, tuning advice, and benchmark discussion.

An open-source project for making AI research agents legible, auditable, and traceable through behavioral code and event logs.

Market-derived RL environments for training agents on quant trading and long-horizon planning under adversarial noise.

A closed-loop controller for LLM training that adapts batch size, learning rate, checkpointing, and pruning to reduce OOM crashes on limited VRAM hardware.

An interactive visualizer showing how a tiny byte-level language model learns 2D token embeddings during training. It includes controls for stepping, pausing, resetting, and adjusting training behavior while plotting the learned vectors.

An open-source simulator that studies how GPT inference behaves under space radiation and cosmic-ray fault conditions, with CLI runs, comparisons, and self-contained HTML reports.