As we described on the title, the model that I have built completely works on iPhone 15 / A16 Bionic, on the other hand it does not run on iPhone 16 / A18 chip with the following error message. E5RT encountered an STL exception. msg = MILCompilerForANE error: failed to compile ANE model using ANEF. Error=_ANECompiler : ANECCompile() FAILED. E5RT: MILCompilerForANE error: failed to compile ANE model using ANEF. Error=_ANECompiler : ANECCompile() FAILED (11) It consumes 1.5 ~ 1.6 GB RAM on the loading the model, then the consumption is decreased to less than 100MB on the both of iPhone 15 and 16. After that, only on iPhone 16, the above error is shown on the Xcode log, the memory consumption is surged to 5 to 6GB, and the system kills the app. It works well only on iPhone 15. This model is built with the Core ML tools. Until now, I have tried the target iOS 16 to 18 and the compute units of CPU_AND_NE and ALL. But any ways have not solved this issue. Eventually, what kindof fix should I do? minimum_deployment_target = ct.target.iOS18 compute_units = ct.ComputeUnit.ALL compute_precision = ct.precision.FLOAT16

Hello, I'm running a large language model (LLM) in Core ML that uses a key-value cache (KV-cache) to store past attention states. The model was converted from PyTorch using coremltools and deployed on-device with Swift. The KV-cache is exposed via MLState and is used across inference steps for efficient autoregressive generation. During the prefill stage — where a prompt of multiple tokens is passed to the model in a single batch to initialize the KV-cache — I’ve noticed that some entries in the KV-cache are not updated after the inference. Specifically: Here are a few details about the setup: The MLState returned by the model is identical to the input state (often empty or zero-initialized) for some tokens in the batch. The issue only happens during the prefill stage (i.e., first call over multiple tokens). During decoding (single-token generation), the KV-cache updates normally. The model is invoked using MLModel.prediction(from:using:options:) for each batch. I’ve confirmed: The prompt tokens are non-repetitive and not masked. The model spec has MLState inputs/outputs correctly configured for KV-cache tensors. Each token is processed in a loop with the correct positional encodings. Questions: Is there any known behavior in Core ML that could prevent MLState from updating during batched or prefill inference? Could this be caused by internal optimizations such as lazy execution, static masking, or zero-value short-circuiting? How can I confirm that each token in the batch is contributing to the KV-cache during prefill? Any insights from the Core ML or LLM deployment community would be much appreciated.

Somehow I'm not able to decrypt our ml models on my machine. It does not matter: If I clean the build / delete the build folder If it's a local build or a build downloaded from our build server I log in as a different user I reboot my system (15.4.1 (24E263) I use a different network Re-generate the encryption keys. I'm the only one in my team confronted with this issue. Using the encrypted models works fine for everyone else. As soon as our application tries to load the bundled ml model the following error is logged and returned: Could not create persistent key blob for CD49E04F-1A42-4FBE-BFC1-2576B89EC233 : error=Error Domain=com.apple.CoreML Code=9 "Failed to generate key request for CD49E04F-1A42-4FBE-BFC1-2576B89EC233 with error: -42908" Error code 9 points to a decryption issue, but offers no useful pointers and suggests that some sort of network request needs to be made in order to decrypt our models. /*! Core ML throws/returns this error when the framework encounters an error in the model decryption subsystem. The typical cause for this error is in the key server configuration and the client application cannot do much about it. For example, a model loading method will throw/return the error when it uses incorrect model decryption key. */ MLModelErrorModelDecryption API_AVAILABLE(macos(11.0), ios(14.0), watchos(7.0), tvos(14.0)) = 9, I could not find a reference to error '-42908' anywhere. ChatGPT just lied to me, as usual... How do can I resolve this or diagnose this further? Thanks.

The documentation for the Create ML tool ("Building an object detector data source") mentions that there are options for using normalized values instead of pixels and also different anchor point origins ("MLBoundingBoxCoordinatesOrigin") instead of always using "center". However, the JSON format for these does not appear in any examples. Does anyone know the format for these options?

Bear with me, please. Please make sure a highly skilled technical person reads and understands this. I want to describe my vision for (AI/Algorithmically) Optimised Operating Systems. To explain it properly, I will describe the process to build it (pseudo). Required Knowledge (no particular order): Processor Logic Circuits, LLM models, LLM tool usage, Python OO coding, Procedural vs OO, NLP fuzzy matching, benchmarking, canvas/artefacts/dynamic HTML interfaces, concepts of how AI models are vastly compressed and miniaturised forms of full data, Algorithmic vs AI. First, take all OO Python code (example) on GitHub (example), then separate each function from each object into its own procedure (procedural logic) by making a logical procedural list of actions to perform only that function based on its entire dependency chain (i.e. all other objects it relies on). Relate all compiled functions using (for example) fuzzy matching on the name, or AI-based functional profiling to get multiple instances of each function. Starting with the most used function, test each one against the others that perform the same task for bugs and completeness. Determine the fastest, most optimal version of that function (and every function). Add a single instance of each most optimal function to the centralised tool codebase, which will later be utilised by the language models. This ensures we rely only on the most optimised function for each and every use case — with every program using one shared instance of that function instead of compiling it separately. In this way, we optimise all existing (Python OO) code based on maximum availability of certain resources. Use the optimised code to teach the AI how to map each user task directly to optimised code (i.e. each user-facing function in unoptimised program code to its optimised version). Later, teach the codebase how to optimise these functions directly to the logic circuits on the processor — as an Operating System — using essentially the same process. Eventually, use the most optimised form for tasks via a dynamic canvas/artefacts UI interface generated by the Start Menu using the language model. Allow custom interfaces to emerge dynamically from the available functions based on language understanding. Grow and optimise the algorithmic codebase until the entire operating system — with versioning — evolves based on the AI-generated user interfaces (compressing them into new versions of the tools codebase). Please don’t give up until you understand this concept completely and nothing in the description is beyond your full comprehension. It’s a highly significant step forward.

When calling NLTagger.requestAssets with some languages, it hangs indefinitely both in the simulator and a device. This happens consistently for some languages like greek. An example call is NLTagger.requestAssets(for: .greek, tagScheme: .lemma). Other languages like french return immediately. I captured some logs from Console and found what looks like the repeated attempts to download the asset. I would expect the call to eventually terminate, either loading the asset or failing with an error.

Hi everyone, I'm trying to use VNDetectTextRectanglesRequest to detect text rectangles in an image. Here's my current code: guard let cgImage = image.cgImage(forProposedRect: nil, context: nil, hints: nil) else { return } let textDetectionRequest = VNDetectTextRectanglesRequest { request, error in if let error = error { print("Text detection error: \(error)") return } guard let observations = request.results as? [VNTextObservation] else { print("No text rectangles detected.") return } print("Detected \(observations.count) text rectangles.") for observation in observations { print(observation.boundingBox) } } textDetectionRequest.revision = VNDetectTextRectanglesRequestRevision1 textDetectionRequest.reportCharacterBoxes = true let handler = VNImageRequestHandler(cgImage: cgImage, orientation: .up, options: [:]) do { try handler.perform([textDetectionRequest]) } catch { print("Vision request error: \(error)") } The request completes without error, but no text rectangles are detected — the observations array is empty (count = 0). Here's a sample image I'm testing with: I expected VNTextObservation results, but I'm not getting any. Is there something I'm missing in how this API works? Or could it be a limitation of this request or revision? Thanks for any help!

Following WWDC24 video "Discover Swift enhancements in the Vision framework" recommendations (cfr video at 10'41"), I used the following code to perform multiple new iOS 18 `RecognizedTextRequest' in parallel. Problem: if more than 2 request are run in parallel, the request will hang, leaving the app in a state where no more requests can be started. -> deadlock I tried other ways to run the requests, but no matter the method employed, or what device I use: no more than 2 requests can ever be run in parallel. func triggerDeadlock() {} try await withThrowingTaskGroup(of: Void.self) { group in // See: WWDC 2024 Discover Siwft enhancements in the Vision framework at 10:41 // ############## THIS IS KEY let maxOCRTasks = 5 // On a real-device, if more than 2 RecognizeTextRequest are launched in parallel using tasks, the request hangs // ############## THIS IS KEY for idx in 0..<maxOCRTasks { let url = ... // URL to some image group.addTask { // Perform OCR let _ = await performOCRRequest(on: url: url) } } var nextIndex = maxOCRTasks for try await _ in group { // Wait for the result of the next child task that finished if nextIndex < pageCount { group.addTask { let url = ... // URL to some image // Perform OCR let _ = await performOCRRequest(on: url: url) } nextIndex += 1 } } } } // MARK: - ASYNC/AWAIT version with iOS 18 @available(iOS 18, *) func performOCRRequest(on url: URL) async throws -> [RecognizedText] { // Create request var request = RecognizeTextRequest() // Single request: no need for ImageRequestHandler // Configure request request.recognitionLevel = .accurate request.automaticallyDetectsLanguage = true request.usesLanguageCorrection = true request.minimumTextHeightFraction = 0.016 // Perform request let textObservations: [RecognizedTextObservation] = try await request.perform(on: url) // Convert [RecognizedTextObservation] to [RecognizedText] return textObservations.compactMap { observation in observation.topCandidates(1).first } } I also found this Swift forums post mentioning something very similar. I also opened a feedback: FB17240843

Hello Apple Developer Community, I'm exploring the integration of Apple Intelligence features into my mobile application and have a couple of questions regarding the current and upcoming API capabilities: Custom Prompt Support: Is there a way to pass custom prompts to Apple Intelligence to generate specific inferences? For instance, can we provide a unique prompt to the Writing Tools or Image Playground APIs to obtain tailored outputs? Direct Inference Capabilities: Beyond the predefined functionalities like text rewriting or image generation, does Apple Intelligence offer APIs that allow for more generalized inference tasks based on custom inputs? I understand that Apple has provided APIs such as Writing Tools, Image Playground, and Genmoji. However, I'm interested in understanding the extent of customization and flexibility these APIs offer, especially concerning custom prompts and generalized inference. Additionally, are there any plans or timelines for expanding these capabilities, perhaps with the introduction of new SDKs or frameworks that allow deeper integration and customization? Any insights, documentation links, or experiences shared would be greatly appreciated. Thank you in advance for your assistance!

Hi, unfortunately I am not able to verify this but I remember some time ago I was able to create CoreML models that had one (or more) inputs with an enumerated shape size, and one (or more) inputs with a static shape. This was some months ago. Since then I updated my MacOS to Sequoia 15.5, and when I try to execute MLModels with this setup I get the following error libc++abi: terminating due to uncaught exception of type CoreML::MLNeuralNetworkUtilities::AsymmetricalEnumeratedShapesException: A model doesn't allow input features with enumerated flexibility to have unequal number of enumerated shapes, but input feature global_write_indices has 1 enumerated shapes and input feature input_hidden_states has 3 enumerated shapes. It may make sense (but not really though) to verify that for inputs with a flexible enumerated shape they all have the same number of possible shapes is the same, but this should not impede the possibility of also having static shape inputs with a single shape defined alongside the flexible shape inputs.

Hi i'm curently crating a model to identify car plates (object detection) i use asitop to monitor my macbook pro and i see that only the cpu is used for the training and i wanted to know why

Hi everyone, I’m an AI engineer working on autonomous AI agents and exploring ways to integrate them into the Apple ecosystem, especially via Siri and Apple Intelligence. I was impressed by Apple’s integration of ChatGPT and its privacy-first design, but I’m curious to know: • Are there plans to support third-party LLMs? • Could Siri or Apple Intelligence call external AI agents or allow extensions to plug in alternative models for reasoning, scheduling, or proactive suggestions? I’m particularly interested in building event-driven, voice-triggered workflows where Apple Intelligence could act as a front-end for more complex autonomous systems (possibly local or cloud-based). This kind of extensibility would open up incredible opportunities for personalized, privacy-friendly use cases — while aligning with Apple’s system architecture. Is anything like this on the roadmap? Or is there a suggested way to prototype such integrations today? Thanks in advance for any thoughts or pointers!

Hello Apple Developer Community, I'm investigating Core ML model loading behavior and noticed that even when the compiled model path remains unchanged after an APP update, the first run still triggers an "uncached load" process. This seems to impact user experience with unnecessary delays. Question: Does Core ML provide any public API to check whether a compiled model (from a specific .mlmodelc path) is already cached in the system? If such API exists, we'd like to use it for pre-loading decision logic - only perform background pre-load when the model isn't cached. Has anyone encountered similar scenarios or found official solutions? Any insights would be greatly appreciated!

Hello Apple Developer Community, I'm investigating Core ML model loading behavior and noticed that even when the compiled model path remains unchanged after an APP update, the first run still triggers an "uncached load" process. This seems to impact user experience with unnecessary delays. Question: Does Core ML provide any public API to check whether a compiled model (from a specific .mlmodelc path) is already cached in the system? If such API exists, we'd like to use it for pre-loading decision logic - only perform background pre-load when the model isn't cached. Has anyone encountered similar scenarios or found official solutions? Any insights would be greatly appreciated!

the specific context is that i would like to build an agent that monitors my phone call (with a customer support for example), and simiply identify whether or not im still put on hold, and notify me when im not. currently after reading the doc, i dont think its possible yet, but im so annoyed by the customer support calls that im willing to go the distance and see if theres any way.

Hello, I was successfully able to compile TKDKid1000/TinyLlama-1.1B-Chat-v0.3-CoreML using Core ML, and it's working well. However, I’m now trying to compile the same model using Swift Transformers. With the limited documentation available on the swift-chat and Hugging Face repositories, I’m finding it difficult to understand the correct process for compiling a model via Swift Transformers. I attempted the following approach, but I’m fairly certain it’s not the recommended or correct method. Could someone guide me on the proper way to compile and use models like TinyLlama with Swift Transformers? Any official workflow, example, or best practice would be very helpful. Thanks in advance! This is the approach I have used: import Foundation import CoreML import Tokenizers @main struct HopeApp { static func main() async { print(" Running custom decoder loop...") do { let tokenizer = try await AutoTokenizer.from(pretrained: "PY007/TinyLlama-1.1B-Chat-v0.3") var inputIds = tokenizer("this is the test of the prompt") print("🧠 Prompt token IDs:", inputIds) let model = try float16_model(configuration: .init()) let maxTokens = 30 for _ in 0..<maxTokens { let input = try MLMultiArray(shape: [1, 128], dataType: .int32) let mask = try MLMultiArray(shape: [1, 128], dataType: .int32) for i in 0..<inputIds.count { input[i] = NSNumber(value: inputIds[i]) mask[i] = 1 } for i in inputIds.count..<128 { input[i] = 0 mask[i] = 0 } let output = try model.prediction(input_ids: input, attention_mask: mask) let logits = output.logits // shape: [1, seqLen, vocabSize] let lastIndex = inputIds.count - 1 let lastLogitsStart = lastIndex * 32003 // vocab size = 32003 var nextToken = 0 var maxLogit: Float32 = -Float.greatestFiniteMagnitude for i in 0..<32003 { let logit = logits[lastLogitsStart + i].floatValue if logit > maxLogit { maxLogit = logit nextToken = i } } inputIds.append(nextToken) if nextToken == 32002 { break } let partialText = try await tokenizer.decode(tokens:inputIds) print(partialText) } } catch { print("❌ Error: \(error)") } } }

Hello folks! Taking a look at https://developer.apple.com/documentation/foundationmodels it’s not clear how to use another models there. Do anyone knows if it’s possible use one trained model from outside (imported) here in foundation models framework? Thanks!

I'm attempting to run a basic Foundation Model prototype in Xcode 26, but I'm getting the error below, using the iPhone 16 simulator with iOS 26. Should these models be working yet? Do I need to be running macOS 26 for these to work? (I hope that's not it) Error: Passing along Model Catalog error: Error Domain=com.apple.UnifiedAssetFramework Code=5000 "There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.MobileAsset.UAF.FM.Overrides" UserInfo={NSLocalizedFailureReason=There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.MobileAsset.UAF.FM.Overrides} in response to ExecuteRequest Playground to reproduce: #Playground { let session = LanguageModelSession() do { let response = try await session.respond(to: "What's happening?") } catch { let error = error } }

I installed Xcode 26.0 beta and downloaded the generative models sample from here: https://developer.apple.com/documentation/foundationmodels/adding-intelligent-app-features-with-generative-models But when I run it in the iOS 26.0 simulator, I get the error shown here. What's going wrong?

Introduced in the Keynote was the 3D Lock Screen images with the kangaroo: https://9to5mac.com/wp-content/uploads/sites/6/2025/06/3d-lock-screen-2.gif I can't see any mention on if this effect is available for developers with an API to convert flat 2D photos in to the same 3D feeling image. Does anyone know if there is an API?