Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Abnormal operation on A12 and lower chips #5

Closed
mazzzystar opened this issue Jul 11, 2023 · 3 comments
Closed

Abnormal operation on A12 and lower chips #5

mazzzystar opened this issue Jul 11, 2023 · 3 comments
Labels
bug Something isn't working enhancement New feature or request

Comments

@mazzzystar
Copy link
Owner

Currently, Queryable does not support devices below the iPhone 11 (with the A13 chip). On these devices, indexing can be built normally, but the search results for any query are the same, and I haven't debugged the problem. If you find a solution, I would greatly appreciate it if you could submit a PR.

@mazzzystar mazzzystar added enhancement New feature or request bug Something isn't working labels Jul 11, 2023
@codingstyle
Copy link
Contributor

Hi,
I managed to make the project work on an iPhone X.
On the TextEncoder init, you need to add the following line to force CPU only on older iPhones.

config.computeUnits = .cpuOnly

Based on information found here:

@mazzzystar
Copy link
Owner Author

Wow! Do we need to use if/else to handle different iPhone devices? Or, if we change this line, would it affect the newer iPhone perfomance?

config.computeUnits = .cpuOnly

BTW, it would be nice if you could submit a PR to fix the issue : )

@codingstyle
Copy link
Contributor

Yeah ideally an if/else is needed to ensure MLModel continues using default configuration on newer iPhones (default is CPU, GPU and Neural Engine).

I will submit a PR later today.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants