ml-explore/mlx

[Feature Request] Fallback for custom kernels

Open

#3,240 建立於 2026年3月11日

在 GitHub 查看
 (0 留言) (0 反應) (0 負責人)C++ (26,216 star) (1,794 fork)batch import
enhancementgood first issue

描述

We have a specific use-case whereby we need to export MLX callables from Linux. Currently, this prevents us from using any operations that require custom kernels (e.g. grid sample) because otherwise, MLX complains that no Metal GPU was found.

Ideally, we would want to keep the fast kernel so that we can export without a Metal GPU, but execute on a Metal GPU.

貢獻者指南

技術棧
cpp
領域
machine learningai
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
C++ knowledgeMLX internalsMetal GPU programming
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
15
研究方向
Research the MLX custom kernel system, specifically how kernels are registered and dispatched. Look at the Metal backend implementation to understand the current limitation. Consider how to create a CPU based fallback using existing array operations or a generic runtime. There are no linked PRs or comments yet.