Daniel Bevenius

@ngxson I'll take a closer look at this today and specifically how about how this could work with a cross-attention model like Llama 3.2 Vision :+1: One thing that is...

@ngxson Sorry about the delay. I've been able to "force" support for mllama using the latest vision api, that is get an example working. I'm now going to iterate on...

@Animaxx Thanks for trying this out! > with xcframework I am able to build the swift example project, but when run it got error: I'm trying to figure this out....

> also when I use the xcframework to build for MacOS app, got error: Ah, I missed building for macos, it currently only builds for ios. I'll try adding a...

@schlu Thanks for reporting this, I'm looking into this now.

@blaineam @schlu I've tried to address the issue both of you ran into with https://github.com/ggml-org/llama.cpp/pull/11996/commits/5cecc8a35916ab826d5295b7777a0be74abc6006. Would you be able to try building/running again with the latest changes and if this...

> Much worse now. I stops right away. Sorry about this (I am running the build locally and checking that the builds work in various projects to try to avoid...

@schlu Can you tell me the version of cmake you are using? I'm asking because I think CMake added official support for visionOS in version 3.28.0. Based on this in...

> I do see this adding my app with the llama.xcframework to App Store Connect. I've not tried this but I'll take a closer look at this tomorrow 👍

With the latest commit I was able to create a project and validate it that uses the xcodeframework: @blaineam Would you be able to try this as well to see...