Product macOS Version macOS 26.4.1 (public release) Hardware Apple M5 Pro, 48 GB unified memory Summary On macOS 26.4.1, the MPS backend consistently reports approximately 40 GiB of “other allocations” on a 48 GB M5 Pro machine, even on a freshly rebooted system with minimal user applications running. This leaves insufficient memory for large GPU tensor operations that previously succeeded on earlier macOS versions. The failure manifests as: RuntimeError: MPS backend out of memory (MPS allocated: 17.60 GiB, other allocations: 40.17 GiB, max allowed: 63.65 GiB). Tried to allocate 7.63 GiB on private pool. The “other allocations: 40.17 GiB” value is consistent across reboots and does not change materially when user applications are quit. This suggests macOS 26.4.1 has increased its baseline GPU/unified memory consumption compared to prior releases in a way that is visible to the MPS allocator. Steps to Reproduce Fresh reboot of M5 Pro, 48 GB, macOS 26.4.1 Launch a PyTorch 2.11.0 application using MPS as the compute device Load a large model into MPS memory (~17 GiB, e.g. a VAE encoder in bfloat16) Attempt to allocate an additional ~7.6 GiB workspace tensor for a matrix multiplication operation (torch.bmm) Result: RuntimeError: MPS backend out of memory, with “other allocations” reported at ~40 GiB despite no large user processes holding GPU memory. Expected: The operation should succeed. 17.60 + 7.63 = 25.23 GiB, which is well within the 48 GiB physical memory of the machine. Additional Observations • vm_stat on a clean boot shows ~24 GB of free system RAM before the PyTorch application launches, consistent with normal OS usage. The 40 GiB figure reported by the MPS allocator as “other allocations” does not correspond to identifiable user processes. • The max allowed: 63.65 GiB ceiling reported by MPS exceeds the physical 48 GiB of the machine, suggesting MPS is using a memory limit calculation that does not account for actual physical constraints on unified memory architectures. • macOS 26.4 introduced a related regression (deterministic RuntimeError: MPSGraph does not support tensor dims larger than INT_MAX) in the same MPS buffer stride arithmetic path. That specific error was resolved in 26.4.1, but the OOM regression described here persists. • This operation succeeded on the same hardware under earlier macOS releases. The increased “other allocations” baseline appears to be specific to macOS 26.x. Impact Machine learning workloads that previously ran successfully on 48 GB Apple Silicon machines are failing on macOS 26.4.1 due to this increased baseline GPU memory consumption. Applications using PyTorch MPS, Core ML, and potentially Metal Performance Shaders directly may be affected. Workaround None identified. Reducing application model size or splitting operations into smaller chunks does not resolve the issue because the constraint is in the “other allocations” baseline, not in the application’s own allocations.

At WWDC25 we launched a new type of Lab event for the developer community - Group Labs. A Group Lab is a panel Q&A designed for a large audience of developers. Group Labs are a unique opportunity for the community to submit questions directly to a panel of Apple engineers and designers. Here are the highlights from the WWDC25 Group Lab for Apple Intelligence. Can I integrate writing tools in my own text editor? UITextView, NSTextView, and SwiftUI TextEditor automatically get Writing Tools on devices that support Apple Intelligence. For custom text editors, check out Enhancing your custom text engine with Writing Tools. Given that Foundation Models are on-device, how will Apple update the models over time? And how should we test our app against the model updates? Model updates are in sync with OS updates. As for testing with updated models, watch our WWDC session about prompt engineering and safety, and read the Human Interface Guidelines to understand best practices in prompting the on-device model. What is the context size of a session in Foundation Models Framework? How to handle the error if a session runs out of the context size? Currently the context size is about 4,000 tokens. If it’s exceeded, developers can catch the .exceededContextWindowSize error at runtime. As discussed in one of our WWDC25 sessions, when the context window is exceeded, one approach is to trim and summarize a transcript, and then start a new session. Can I do image generation using the Foundation Models Framework or is only text generation supported? Foundation Models do not generate images, but you can use the Foundation Models framework to generate prompts for ImageCreator in the Image Playground framework. Developers can also take advantage of Tools in Foundation Models framework, if appropriate for their app. My app currently uses a third party server-based LLM. Can I use the Foundation Models Framework as well in the same app? Any guidance here? The Foundation Models framework is optimized for a subset of tasks like summarization, extraction, classification, and tagging. It’s also on-device, private, and free. But at 3 billion parameters it isn’t designed for advanced reasoning or world knowledge, so for some tasks you may still want to use a larger server-based model. Should I use the AFM for my language translation features given it does text translation, or is the Translation API still the preferred approach? The Translation API is still preferred. Foundation Models is great for tasks like text summarization and data generation. It’s not recommended for general world knowledge or translation tasks. Will the TranslationSession class introduced in ios18 get any new improvments in performance or reliability with the new live translation abilities in ios/macos/ipados 26? Essentially, will we get access to live translation in a similar way and if so, how? There's new API in LiveCommunicationKit to take advantage of live translation in your communication apps. The Translate framework is using the same models as used by Live Communication and can be combined with the new SpeechAnalyzer API to translate your own audio. How do I set a default value for an App Intent parameter that is otherwise required? You can implement a default value as part of your parameter declaration by using the @Parameter(defaultValue:) form of the property wrapper. How long can an App Intent run? On macOS there is no limit to how long app intents can run. On iOS, there is a limit of 30 seconds. This time limit is paused when waiting for user interaction. How do I vary the options for a specific parameter of an App Intent, not just based on the type? Implement a DynamicOptionsProvider on that parameter. You can add suggestedEntities() to suggest options. What if there is not a schema available for what my app is doing? If an app intent schema matching your app’s functionality isn’t available, take a look to see if there’s a SiriKit domain that meets your needs, such as for media playback and messaging apps. If your app’s functionality doesn’t match any of the available schemas, you can define a custom app intent, and integrate it with Siri by making it an App Shortcut. Please file enhancement requests via Feedback Assistant for new App intent schemas that would benefit your app. Are you adding any new app intent domains this year? In addition to all the app intent domains we announced last year, this year at WWDC25 we announced that Visual Intelligence will be added to iOS 26 and macOS Tahoe. When my App Intent doesn't show up as an action in Shortcuts, where do I start in figuring out what went wrong? App Intents are statically extracted. You can check the ExtractMetadata info in Xcode's build log. What do I need to do to make sure my App Intents work well with Spotlight+? Check out our WWDC25 sessions on App Intents, including Explore new advances in App Intents and Develop for Shortcuts and Spotlight with App Intents. Mostly, make sure that your intent can run from the parameter summary alone, no required parameters without default values that are not already in the parameter summary. Does Spotlight+ on macOS support App Shortcuts? Not directly, but it shows the App Intents your App Shortcuts are sitting on top of. I’m wondering if the on-device Foundation Models framework API can be integrated into an app to act strictly as an app in-universe AI assistant, responding only within the boundaries of the app’s fictional context. Is such controlled, context-limited interaction supported? FM API runs inside the process of your app only and does not automatically integrate with any remaining part of the system (unless you choose to implement your own tool and utilize tool calling). You can provide any instructions and prompts you want to the model. If a country does not support Apple Intelligence yet, can the Foundation Models framework work? FM API works on Apple Intelligence-enabled devices in supported regions and won’t work in regions where Apple Intelligence is not yet supported

I'm really not familiar with ML, but I need a model that can enhance and denoise 4k video stream at 30fps. I have tried to search latest papers but they all have very complex structure, and I don't think I can convert them to mlmodel. So can anyone give me any recommandation for such models? If there is an existing mlmodel, that would be great!

I am excited to share that I have developed a Metal kernel for Flash Attention that eliminates race conditions and fully leverages Apple Silicon’s shared memory and registers. This kernel can dramatically accelerate training of transformer-based models. Early benchmarks suggest that models which previously required months to train could see reductions to just a few hours on Apple hardware, while maintaining numerical stability and accuracy. I plan to make the code publicly available to enable the broader community to benefit. I would be happy to keep you updated on the latest developments and improvements as I continue testing and optimizing the kernel. I believe this work could provide valuable insights for Apple’s machine learning research and products.

Hi, I'm stuck distributing a custom FoundationModels adapter as an Apple-hosted managed asset pack via TestFlight. Everything looks correctly configured end to end but the download just never starts and the statusUpdates sequence is silent. Here's my configuration: App Info.plist: <key>BAHasManagedAssetPacks</key><true/> <key>BAUsesAppleHosting</key><true/> <key>BAAppGroupID</key><string>group.com.fiuto.shared</string> Entitlement com.apple.developer.foundation-model-adapter on both the app and the asset downloader extension. The asset downloader extension uses StoreDownloaderExtension , returning SystemLanguageModel.Adapter.isCompatible(assetPack) from shouldDownload , and the app group on app and asset download extension is the same. I have exported the adapter with toolkit 26.0.0, obtaining: adapterIdentifier = fmadapter-FiutoAdapter-1234567 I have packaged the asset pack using xcrun ba-package and uploaded it to App Store Connect via Transporter, and I get the "ready for internal and external testing" state on App Store Connect, and I have uploaded my app build on TestFlight after the asset pack was marked as ready. I used this code: let adapter = try SystemLanguageModel.Adapter(name: "FiutoAdapter") let ids = SystemLanguageModel.Adapter.compatibleAdapterIdentifiers(name: "FiutoAdapter") // ids == ["fmadapter-FiutoAdapter-1234567"] for await status in AssetPackManager.shared.statusUpdates(forAssetPackWithID: ids.first!) { } I expect the download to start and the stream to yield first .began, then .downloading(progress) and .finished. Actually, compatibleAdapterIdentifiers returns the correct ID, the stream is correctly acquired but i get zero events, so no .began/.downloading/.failed/.finished. Important things: I don't get any error in Console as well; I tested this as an internal tester on TestFlight Tested on iPhone 16 Pro, running iOS 26.3.1 - more than 50GB of free space Apple Intelligence is enabled and set in Italian Background downloads are enabled. I've already checked if the adapter identifier matches regex fmadapter-\w+-\w+ , i tried to reinstall the build, rebooting the device, reupload the asset pack, and also checked that the foundation models adapter entitlement is present on both targets. Is there a known way to diagnose why statusUpdates is silent (no log subsystem seems to show why) in this exact configuration? Is there maybe any delay between asset pack approval on App Store Connect and availability to TestFlight internal testers that I do not know of? I've checked other threads for applicable solutions and I've found that this is similar to the symptom reported in this thread: https://developer.apple.com/forums/thread/805140 / (FB20865802) and also i'm internal tester and on stable iOS 26.3.1, so the limitations from this thread: https://developer.apple.com/forums/thread/793565 shouldn't apply. Thanks

Problem: CoreML produces NaN on GPU (works fine on CPU) when running transformer attention with fused QKV projection on macOS 26.2. Root cause: The common::fuse_transpose_matmul optimization pass triggers a Metal kernel bug when sliced tensors feed into matmul(transpose_y=True). Workaround: pipeline = ct.PassPipeline.DEFAULT pipeline.remove_passes(['common::fuse_transpose_matmul']) mlmodel = ct.convert(model, ..., pass_pipeline=pipeline) Minimal repro: https://github.com/imperatormk/coreml-birefnet/blob/main/apple_bug_repro.py Affected: Any ViT/Swin/transformer with fused QKV attention (BiRefNet, etc.) Has anyone else hit this? Filed FB report too.

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!

I've built an iOS app with a novel approach to AI safety: a deterministic, pre-inference validation layer called Newton Engine. Instead of relying on the LLM to self-moderate, Newton validates every prompt BEFORE it reaches the model. It uses shape theory and semantic analysis to detect: • Corrosive frames (self-harm language patterns) • Logical contradictions (requests that undermine themselves) • Delegation attempts (asking AI to make human decisions) • Jailbreak patterns (prompt injection, role-play escapes) • Hallucination triggers (requests for fabricated citations) The system achieves a 96% adversarial catch rate across 847 test cases, with zero false positives on benign prompts. Key technical details: • Pure Swift/SwiftUI, no external dependencies • Runs entirely on-device (no server calls for validation) • Deterministic (same input always produces same output) • Auditable (full trace logging for every validation) I'm preparing to submit to the App Store and wanted to ask: Are there specific App Review guidelines I should reference for AI safety claims? Is there interest from Apple in deterministic governance layers for Apple Intelligence integration? Any recommendations for demonstrating safety compliance during review? The app is called Ada, and the engine is open source at: github.com/jaredlewiswechs/ada-newton Happy to share technical documentation or discuss the architecture with anyone interested. See: parcri.net

JAX Metal shows 55x slower random number generation compared to NVIDIA CUDA on equivalent workloads. This makes Monte Carlo simulations and scientific computing impractical on Apple Silicon. Performance Comparison NVIDIA GPU: 0.475s for 12.6M random elements M1 Max Metal: 26.3s for same workload Performance gap: 55x slower Environment Apple M1 Max, 64GB RAM, macOS Sequoia Version 15.6.1 JAX 0.4.34, jax-metal latest Backend: Metal Reproduction Code import time import jax import jax.numpy as jnp from jax import random key = random.PRNGKey(42) start_time = time.time() random_array = random.normal(key, (50000, 252)) duration = time.time() - start_time print(f"Duration: {duration:.3f}s")

WWDC25: Combine Metal 4 machine learning and graphics Demonstrated a way to combine neural network in the graphics pipeline directly through the shaders, using an example of Texture Compression. However there is no mention of using which ML technique texture is compressed. Can anyone point me to some well known model/s for this particular use case shown in WWDC25.

It seems to be that Swift has more APIs implemented than the C++ interface (especially APIs found in the MLXNN and MLXOptimize folders). Is there any intention to implement more APIs for neural networks and training them in the future?

I'm trying to use Apple's new Visual Intelligence API for recommending content through screenshot image search. The problem I encountered is that the SemanticContentDescriptor labels are either completely empty or super misleading, making it impossible to query for similar content on my app. Even the closest matching example was inaccurate, returning a single label ["cardigan"] for a Supreme T-Shirt. I see other apps using this API like Etsy for example, and I'm wondering if they're using the input pixel buffer to query for similar content rather than using the labels? If anyone has a similar experience or something that wasn't called out in the documentation please lmk! Thanks.

While analyzing system power on an M4 Max under GPU-heavy compute workloads, I noticed that the the GPU power reported by powermetrics does not come anywhere close to total system DC power reported by the SMC counter PDTR (as used by utilities like mactop). For example, in a heavy GPU workload, powermetrics would report a 65W idle-load delta on the GPU, but at the same time system DC power would rise by 179W, leaving 114W or nearly 2/3 of total system DC power on a Mac Studio M4 Max unexplained. From measurements, the difference appears to correlate with the amount of on-chip data movement (for example, varying bytes-per-FLOP in the workload changes the observed gap). Using SMC and IOReport, I was able to reverse engineer an energy model for the GPU that explains almost all of the energy flow with less than 2% error on the workload I studied. The result is a simple two-term energy roofline model: P_GPU (GPU_combined term in the plot) ≈ a * bytes + b * FLOPs with: ~5 pJ/byte for SRAM movement ~2.7 pJ/FLOP for compute. Has anyone observed similar behavior, or is there guidance on how GPU power reported by IOReport/powermetrics should be interpreted relative to total system power? In particular, I’m interested in whether certain classes of GPU activity may not be attributed to the GPU component in IOReport. Full details with the methodology and results are available here: https://youtu.be/HKxIGgyeISM

I'm downloading a fine-tuned model from HuggingFace which is then cached on my Mac when the app first starts. However, I wanted to test adding a progress bar to show the download progress. To test this I need to delete the cached model. From what I've seen online this is cached at /Users/userName/.cache/huggingface/hub However, if I delete the files from here, using Terminal, the app still seems to be able to access the model. Is the model cached somewhere else? On my iPhone it seems deleting the app also deletes the cached model (app data) so that is useful.

We built an open-source macOS menu bar app that turns speech into text and pastes it into the active app — using SpeechAnalyzer for on-device transcription, ScreenCaptureKit + Vision for screen-aware context, and FluidAudio for speaker diarization in meeting mode. Here's what we learned shipping it on macOS 26. GitHub: github.com/Marvinngg/ambient-voice Architecture The app has two modes: hotkey dictation (press to talk, release to inject) and meeting recording (continuous transcription with a floating panel). Dictation Mode Audio capture uses AVCaptureSession (more on why below). The captured audio feeds into SpeechAnalyzer via an AsyncStream: let transcriber = SpeechTranscriber( locale: locale, transcriptionOptions: [], reportingOptions: [.volatileResults, .alternativeTranscriptions], attributeOptions: [.audioTimeRange, .transcriptionConfidence] ) let analyzer = SpeechAnalyzer(modules: [transcriber]) let (inputSequence, inputBuilder) = AsyncStream.makeStream() try await analyzer.start(inputSequence: inputSequence) While recording, we capture a screenshot of the focused window using ScreenCaptureKit, run Vision OCR (VNRecognizeTextRequest), extract keywords, and inject them into SpeechAnalyzer as contextual bias: let context = AnalysisContext() context.contextualStrings[.general] = ocrKeywords try await analyzer.setContext(context) This improves accuracy for technical terms and proper nouns visible on screen. If your screen shows "SpeechAnalyzer", saying it out loud is more likely to be transcribed correctly. After transcription, an optional L2 step sends the text through a local LLM (ollama) for spoken-to-written cleanup, then CGEvent simulates Cmd+V to paste into the active app. Meeting Mode Meeting mode forks the same audio stream to two consumers: SpeechAnalyzer — real-time streaming transcription, displayed in a floating NSPanel FluidAudio buffer — accumulates 16kHz Float32 mono samples for batch speaker diarization after recording stops When the user ends the meeting, FluidAudio's performCompleteDiarization() runs on the accumulated audio. We align transcription segments with speaker segments using audioTimeRange overlap matching — each transcription segment gets assigned the speaker ID with the most time overlap. Results export to Markdown. Pitfalls We Hit on macOS 26 1. AVAudioEngine installTap doesn't fire with Bluetooth devices We started with AVAudioEngine.inputNode.installTap() for audio capture. It worked fine with built-in mics but the tap callback never fired with Bluetooth devices (tested with vivo TWS 4 Hi-Fi). Fix: switched to AVCaptureSession. The delegate callback captureOutput(_:didOutput:from:) fires reliably regardless of audio device. The tradeoff is you get CMSampleBuffer instead of AVAudioPCMBuffer, so you need a conversion step. 2. NSEvent addGlobalMonitorForEvents crashes Our global hotkey listener used NSEvent.addGlobalMonitorForEvents. On macOS 26, this crashes with a Bus error inside GlobalObserverHandler — appears to be a Swift actor runtime issue. Fix: switched to CGEventTap. Works reliably, but the callback runs on a CFRunLoop context, which Swift doesn't recognize as MainActor. 3. CGEventTap callbacks aren't on MainActor If your CGEventTap callback touches any @MainActor state, you'll get concurrency violations. The callback runs on whatever thread owns the CFRunLoop. Fix: bridge with DispatchQueue.main.async {} inside the tap callback before touching any MainActor state. 4. CGPreflightScreenCaptureAccess doesn't request permission We used CGPreflightScreenCaptureAccess() as a guard before calling ScreenCaptureKit. If it returned false, we'd bail out. The problem: this function only checks — it never triggers macOS to add your app to the Screen Recording permission list. Chicken-and-egg: you can't get permission because you never ask for it. Fix: call CGRequestScreenCaptureAccess() at app startup. This adds your app to System Settings → Screen Recording. Then let ScreenCaptureKit calls proceed without the preflight guard — SCShareableContent will also trigger the permission prompt on first use. 5. Ad-hoc signing breaks TCC permissions on every rebuild During development, codesign --sign - (ad-hoc) generates a different code directory hash on every build. macOS TCC tracks permissions by this hash, so every rebuild = new app identity = all permissions reset. Fix: sign with a stable certificate. If you have an Apple Development certificate, use that. The TeamIdentifier stays constant across rebuilds, so TCC permissions persist. We also discovered that launching via open WE.app (LaunchServices) instead of directly executing the binary is required — otherwise macOS attributes TCC permissions to Terminal, not your app. Benchmarks We ran end-to-end benchmarks on public datasets (Mac Mini M4 16GB, macOS 26): Transcription (SpeechAnalyzer, AliMeeting Chinese): • Near-field CER 34% (excluding outliers ~25%) • Far-field CER 40% (single channel, no beamforming, >30% overlap) • Processing speed 74-89x real-time Speaker diarization (FluidAudio offline): • AMI English 16 meetings: avg DER 23.2% (collar=0.25s, ignoreOverlap=True) • AliMeeting Chinese 8 meetings: DER 48.5% (including overlap regions) • Memory: RSS ~500MB, peak 730-930MB Full evaluation methodology, scripts, and raw results are in the repo. Open Source The project is MIT licensed: github.com/Marvinngg/ambient-voice It includes the macOS client (Swift 6.2, SPM), server-side distillation/training scripts (Python), and a complete evaluation framework with reproducible benchmarks. Feedback and contributions welcome.

Hi everyone, I believe I’ve encountered a potential bug or a hardware alignment limitation in the Core ML Framework / ANE Runtime specifically affecting the new Stateful API (introduced in iOS 18/macOS 15). The Issue: A Stateful mlprogram fails to run on the Apple Neural Engine (ANE) if the state tensor dimensions (specifically the width) are not a multiple of 32. The model works perfectly on CPU and GPU, but fails on ANE both during runtime and when generating a Performance Report in Xcode. Error Message in Xcode UI: "There was an error creating the performance report Unable to compute the prediction using ML Program. It can be an invalid input data or broken/unsupported model." Observations: Case A (Fails): State shape = (1, 3, 480, 270). Prediction fails on ANE. Case B (Success): State shape = (1, 3, 480, 256). Prediction succeeds on ANE. This suggests an internal memory alignment or tiling issue within the ANE driver when handling Stateful buffers that don't meet the 32-pixel/element alignment. Reproduction Code (PyTorch + coremltools): import torch.nn as nn import coremltools as ct import numpy as np class RNN_Stateful(nn.Module): def __init__(self, hidden_shape): super(RNN_Stateful, self).__init__() # Simple conv to update state self.conv1 = nn.Conv2d(3 + hidden_shape[1], hidden_shape[1], kernel_size=3, padding=1) self.conv2 = nn.Conv2d(hidden_shape[1], 3, kernel_size=3, padding=1) self.register_buffer("hidden_state", torch.ones(hidden_shape, dtype=torch.float16)) def forward(self, imgs): self.hidden_state = self.conv1(torch.cat((imgs, self.hidden_state), dim=1)) return self.conv2(self.hidden_state) # h=480, w=255 causes ANE failure. w=256 works. b, ch, h, w = 1, 3, 480, 255 model = RNN_Stateful((b, ch, h, w)).eval() traced_model = torch.jit.trace(model, torch.randn(b, 3, h, w)) mlmodel = ct.convert( traced_model, inputs=[ct.TensorType(name="input_image", shape=(b, 3, h, w), dtype=np.float16)], outputs=[ct.TensorType(name="output", dtype=np.float16)], states=[ct.StateType(wrapped_type=ct.TensorType(shape=(b, ch, h, w), dtype=np.float16), name="hidden_state")], minimum_deployment_target=ct.target.iOS18, convert_to="mlprogram" ) mlmodel.save("rnn_stateful.mlpackage") Steps to see the error: Open the generated .mlpackage in Xcode 16.0+. Go to the Performance tab and run a test on a device with ANE (e.g., iPhone 15/16 or M-series Mac). The report will fail to generate with the error mentioned above. Environment: OS: macOS 15.2 Xcode: 16.3 Hardware: M4 Has anyone else encountered this 32-pixel alignment requirement for StateType tensors on ANE? Is this a known hardware constraint or a bug in the Core ML runtime? Any insights or workarounds (other than manual padding) would be appreciated.

I am a professional user of the 2019 Mac Pro (7,1) with dual AMD Radeon Pro W6900X MPX modules (32GB VRAM each). This hardware is designed for high-performance compute, but it is currently crippled for modern local LLM/AI workloads under Linux due to Apple's EFI/PCIe routing restrictions. Core Issue: rocminfo reports "No HIP GPUs available" when attempting to use ROCm/amdgpu on Linux Apple's custom EFI firmware blocks full initialization of professional GPU compute assets The dual W6900X GPUs have 64GB combined VRAM and high-bandwidth Infinity Fabric Link, but cannot be fully utilized for local AI inference/training My Specific Request: Apple should provide an official, one-click deployable application that enables full utilization of dual W6900X GPUs for local large language model (LLM) inference and training under Linux. This application must: Fully initialize both W6900X GPUs via HIP/ROCm, establishing valid compute contexts Bypass artificial EFI/PCIe routing restrictions that block access to professional GPU resources Provide a stable, user-friendly one-click deployment experience (similar to NVIDIA's AI Enterprise or AMD's ROCm Hub) Why This Matters: The 2019 Mac Pro is Apple's flagship professional workstation, marketed for compute-intensive workloads. Its high-cost W6900X GPUs should not be locked down for modern AI/LLM use cases. An official one-click deployment solution would demonstrate Apple's commitment to professional AI and unlock significant value for professional users. I look forward to Apple's response and a clear roadmap for enabling this critical capability. #MacPro #Linux #ROCm #LocalLLM #W6900X #CoreML

I am developing a macOS application using SwiftUI (with an iOS version as well). One feature we are exploring is displaying an avatar that reads or speaks dynamically generated text produced by an AI service. The basic flow would be: Text generated by an AI service Text converted to speech using a TTS engine An avatar (2D or 3D) rendered in the app that animates lip movement synchronized with the speech Ideally the avatar would render locally on the device. Questions: What Apple frameworks would be most appropriate for implementing a speaking avatar? SceneKit RealityKit SpriteKit (for 2D avatars) Is there any recommended way to drive lip-sync animation from speech audio using Apple frameworks? Does AVSpeechSynthesizer expose phoneme or viseme timing information that could be used for avatar animation? If such timing information is not available, what is the recommended approach for synchronizing character mouth animation with speech audio on macOS/iOS? Are there examples of real-time character animation synchronized with speech on macOS/iOS? Any architectural guidance or references would be greatly appreciated.

Hi, I'm building ANF (Autonomous Native Forge) — a cloud-free, 4-agent autonomous software production pipeline running on local hardware with local LLM inference. No middleware, pure Node.js native. Currently running on NVIDIA Blackwell GB10 with vLLM + DeepSeek-R1-32B. Now porting to Apple Silicon. Three technical questions: How production-ready is mlx-lm's OpenAI-compatible API server for long context generation (32K tokens)? What's the recommended approach for KV Cache management with Unified Memory architecture — any specific flags or configurations for M4 Ultra? MLX vs GGUF (llama.cpp) for a multi-agent pipeline where 4 agents call the inference endpoint concurrently — which handles parallel requests better on Apple Silicon? GitHub: github.com/trgysvc/AutonomousNativeForge Any guidance appreciated.

Looking for help with or to help with, due to the pending document enhancement, the Vibe Coders edition of cml editor. Also for more information on how to use the .mlkey whether or not my model is suppose to say IOs18 when I am planning to use it on Mac Apple Intelligence seems to think coreML is for iOS but are the capabilities extended when running NPU on the book? How to use this graph. coming in hot sorry. btw. there are 100s of feedback and crash reports sent in form me for additional info? I attached a image that might help with updating Tags