AI-Hypercomputer

Use this skill when asked to generate or update release notes in docs/release_notes.md with major changes, new features, architecture updates, performance improvements, bug fixes, and deprecations.

Performs new LLM/VLM model bring-up in MaxText on TPU VMs. Use when onboarding a new HuggingFace model (e.g., Qwen, Llama, Gemma variants) to MaxText. This includes analyzing the HuggingFace source code, implementing decoder layers in JAX/Flax, writing…

Orchestrates Pallas TPU kernel development and optimization. Converts JAX, PyTorch or CUDA into a Pallas TPU kernel and runs a self-refinement loop (plan -> implement -> compile -> test -> autotune -> profile) by dispatching the maxkernel-worker subagent once…