ml-explore/mlx

[Feature Request] Fallback for custom kernels

Closed

#3,240 opened on Mar 11, 2026

View on GitHubContributor guide
 (4 comments) (0 reactions) (0 assignees)C++ (1,794 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (26,216 stars)
PR merge metrics
 (Avg merge 6d 17h) (75 merged PRs in 30d)

Description

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.

Contributor guide

Research direction
Investigate how custom kernels are compiled and executed in MLX, then design a fallback mechanism that uses software implementation or CPU based kernels when Metal GPU is not available. Focus on the grid sample operation and similar custom kernels.
Tech stack
None
Domain
machine learningbackend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30