Mlx Vlm plugin for Grok Build

Skills (8)

• add-new-model — Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face model_type to a new file under mlx_vlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing m
• benchmarking — Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, p
• cli-inference — Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlx_vlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors
• contributing — Use this skill when the user wants to contribute to MLX-VLM — opening a PR, where model code/config/tests go, backward-compatible config args, running the test suite, code formatting and the pre-commit hooks (black, clang-format), and PR ex
• convert-quantize — Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlx_vlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts,
• hf-cache-models — Use this skill when the user wants to list, inspect, or report cached, custom, or loaded MLX-VLM models through the server's model discovery endpoint.
• reproducible-github-issues — Use this skill when the user wants to create, improve, or triage a reproducible GitHub issue for MLX-VLM, including bug reports from CLI inference, server inference, model loading, processors, media inputs, dependency setup, crashes, wrong
• server-inference — Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlx_vlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload