ml-explore / ml-explore/mlx

[BUG] crash while using new_stream

Open
#2,118 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
C++
Stars
28.5k
Forks
2.3k
Avg merge
3d 8h
Merged PRs (30d)
62

Description

Describe the bug

crash while using new_stream -- I was trying to replicate something from the swift side and I can see the same error there.

To Reproduce

Include code snippet

import mlx.core as mx

i = 0
while True:
	print(i)

	s = mx.new_stream(mx.gpu)
	x = mx.random.uniform(shape=[10, 10]).sum(stream=s)
	_ = x.item()

	i += 1
...
607
608
609
libc++abi: terminating due to uncaught exception of type std::runtime_error: [METAL] Command buffer execution failed: Internal Error (0000010a:Internal Error)
[1]    10855 abort      python /tmp/t.py

Expected behavior

No crash

Desktop (please complete the following information):

  • OS Version: macOS 15.4
  • Version 0.25.0

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No source file or test is named. Start by running the reproduction with Python, MLX 0.25.0, macOS 15.4, and the mx.new_stream/mx.gpu calls; compare the failure around iteration 609. Done means the loop completes without the Metal command-buffer crash.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.