菜单
Run and compare MLX Vulkan inference benchmarks. Use when asked to benchmark this repository, measure a change, run bf16 or 8-bit MLX performance tests, or compare current results with the README baseline.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Review the MLX Vulkan backend for one major async-pipeline or inference-performance issue, obtain user approval, implement the scoped fix, then run full MLX validation, benchmarks, and model generation reporting. Use when the user wants an end-to-end Vulkan improvement workflow with an explicit review-before-fix approval boundary.
Commit changes solely within the MLX submodule in this Vulkan repository. Use when asked to inspect, stage, and commit work in `mlx/` without modifying or committing the `mlx-vulkan` parent repository.
Commit MLX submodule changes, run required Vulkan benchmarks, push a branch, and open a PR against `goniz/mlx`. Use when asked to create a pull request for MLX Vulkan work, especially when an issue number must be closed and bf16 plus 8-bit benchmark results are required.
Build MLX, reproduce one failing C++ test, and implement the smallest Vulkan-only fix. Use when asked to repair a C++ test failure in this repository while preserving test code and avoiding unrelated fixes.
Build MLX, reproduce one failing Python test, and implement the smallest Vulkan-only fix. Use when asked to repair a Python test failure in this repository while preserving test code and avoiding unrelated fixes.
Investigate and address a `goniz/mlx-vulkan` GitHub issue in the MLX submodule. Use when given an issue number and asked to read the issue, plan the work, reproduce a reported bug, implement the scoped fix, and work from an MLX feature branch based on `goniz/mlx:feat/vulkan`.
| name | mlx-benchmark |
| description | Run and compare MLX Vulkan inference benchmarks. Use when asked to benchmark this repository, measure a change, run bf16 or 8-bit MLX performance tests, or compare current results with the README baseline. |
Run benchmarks through ./dev.sh only. Treat any user-supplied model or benchmark option as an override; otherwise run both standard precisions.
README.md and identify the relevant current baseline numbers../dev.sh benchmark bf16../dev.sh benchmark 8bit../dev.sh benchmark already serializes via /tmp/mlx-gpu/gpu.lock (shared with CI); still launch them one after another so waiters are ordered intentionally.Report the commands run, results for each precision, the baseline used, and the performance difference. Do not change code unless explicitly asked.