top | item 46854898

(no title)

zcbenz | 29 days ago

It is a bug in MLX that has been fixed a few days ago: https://github.com/ml-explore/mlx/pull/3083

discuss

order

zozbot234|29 days ago

So the underlying issue is that the iPhone 16 Pro SKU was misdetected as having Neural Accelerator (nax) support and this caused silently wrong results. Not a problem with the actual hardware.

TimByte|29 days ago

From a debugging point of view, the author's conclusion was still completely reasonable given the evidence they had

llm_nerd|29 days ago

Apple's documentation is utter garbage, but this code almost seems like a separate issue (and notably the MLX library uses loads of undocumented properties in metal which isn't cool). It looks like the change used to allow the NAX kernel to be used on the iPhone 17 or upcoming 18 if you're on 26.2 or later, to instead only allow it on the iPhone 17 Pro or upcoming 18. I'm fairly sure the GPU arch on the A19 is 17. They changed it so it will only use that kernel on the 17 Pro or upcoming 18, which is notable as the A19 Pro in the 17 Pro has a significantly changed GPU, including GPU tensor cores. The only real change here is that it would limit to the pro variants for the "17" model.

embedding-shape|29 days ago

Blog post dated 28 Jan 2026, the bug fix posted 29 Jan 2026, so I guess this story had a happy ending :)

Still, sad state of affairs that it seems like Apple is still fixing bugs based on what blog posts gets the most attention on the internet, but I guess once they started that approach, it's hard to stop and go back to figuring out priorities on their own.

dahcryn|29 days ago

I think you overestimate the power of a blogpost and the speed of bugfixing at Apple for something like this.

I almost guarantee there is no way they can read this blogpost, escalate it internally, get the appropriate approval to the work item, actually work on the fix, get it through QA and get it live in production in 3 days. That would only happen on really critical issues, and this is definitely not critical enough for that.

jckahn|29 days ago

Just goes to show that attention is all you need.

llm_nerd|29 days ago

MLX is a fairly esoteric library seeing very little usage, mostly to try to foment a broader NN space on Apple devices. This isn't something that is widely affecting people, and most people simply aren't trying to run general LLMs on their iPhone.

I don't think that fix is specific to this, but it's absolutely true that MLX is trying to lever every advantage it can find on specific hardware, so it's possible it made a bad choice on a particular device.

rafaelcosta|29 days ago

Extremely bad timing on my end then, should've waited for a few more days

mrtesthah|29 days ago

How do you know that it wasn’t merely that the blog post elicited multiple people to file the same duplicate bug in Apple’s radar system, which is how they ostensibly prioritize fixes?

liuliu|28 days ago

Why MLX doesn't just detect apple10 support (for Metal)? That excludes all the devices without NA.

syntaxing|29 days ago

Kinda sucks how it seems like there’s no CI that runs on hardware.