Environment: macOS 27.0 beta (26A5368g) Xcode 27 beta — Instruments 27.0 (64578.226), build 27A5209h MacBook Pro (M1, 2020), 16 GB — MacBookPro17,1 Target: physical iPhone running an iOS app (on-device LLM inference benchmarking) Summary: Instruments crashes reproducibly with EXC_BREAKPOINT (SIGTRAP) shortly after I stop a recording. Recording itself works — the crash occurs during the post-stop analysis phase, while the trace is being processed. This has happened multiple times today with different templates (Time Profiler, and a custom document with Power Profiler / os_signpost / Thermal State). Steps to reproduce: Open Instruments 27.0 beta, choose Time Profiler (or a document containing Power Profiler + os_signpost) Target a physical iPhone and an installed app Record for a short period, then press Stop Instruments crashes while analyzing/importing the trace Crash details: The crashing thread is always on the dispatch queue com.apple.dt.frame.activity, inside InstrumentsPlugIn transformer/modeler code. In one report the crashing frame is: Thread 10 Crashed:: Dispatch queue: com.apple.dt.frame.activity 0 InstrumentsPlugIn NetworkConnectionStatsModeling.__receiveRow(cursor:writer:referenceManager:) + 920 1 InstrumentsPlugIn TransformerExecutionUnit.run(yieldBlock:) + 92 2 InstrumentsPlugIn specialized TransformerHostingModeler.populateOutputTables(_:usingObserverations:parameters:checkToYieldBlock:) + 2344 Exception Type: EXC_BREAKPOINT (SIGTRAP), esr 0xf2000001 (Breakpoint) brk 1 At crash time, sibling worker threads on the same queue were executing SystemPowerImpactModeling and ProcessSubsystemImpactModeling transformers, so the failure appears to be in the modeling pipeline that runs when the recording is finalized. Incident identifiers from two occurrences today: D6D2467F-8553-487C-A291-EC30C0D2846F (14:13 IST) 55017CAB-5345-4865-9695-36228B B80AA4A (18:20 IST) Filed via Feedback Assistant as FBXXXXXXXX with full crash logs and sysdiagnose attached. Questions: Is this a known issue in the current Instruments 27.0 beta? Is there a recommended workaround to record and analyze traces until a fix ships — e.g., recording headlessly with xctrace and opening the .trace in a late r build? Happy to provide the .trace files or additional diagnostics. Thanks!

Hi everyone, I am developing a benchmarking tool to measure memory latency (L1/L2/DRAM) on Apple Silicon. I am currently using Xcode Instruments (CPU Counters) to validate my results. In my latest run for a 128 MB buffer with random access, Instruments shows: Latency (cycles): ~259 cycles (derived from LDST_UNIT_OLD_L1D_CACHE_MISS / L1D_CACHE_MISS_LD). Manual Timer Result: ~80 ns. To correlate these two values, I need the exact CPU Frequency (GHz) at the time of the sample. My Questions: Is there a recommended way to programmatically fetch the current frequency of the Performance cores (p-cores) during a benchmark run? Does Apple provide a "nominal" frequency value for M-series chips that we should use for cycle-to-nanosecond conversions? In Instruments, is there a hidden counter or "Average Frequency" metric that I can enable to avoid manual math? Hardware/Software Environment: Tool: Instruments 26.3+ (CPU Counters Template). Chip: A19, iPhone 17 pro. OS: 26.3.

Apple's Image Playground primarily performs image generation on-device, but can use secure Private Cloud Compute for more complex requests that require larger models. Private Cloud Compute (PCC) For more complex tasks that require greater computational power than the device can provide, Image Playground leverages Apple's Private Cloud Compute. This system extends the privacy and security of the device to the cloud: Secure Environment: PCC runs on Apple silicon servers and uses a secure enclave to protect data, ensuring requests are processed in a verified, secure environment. No Data Storage: Data is never stored or made accessible to Apple when using PCC; it is used only to fulfill the specific request. Independent Verification: Independent experts are able to inspect the code running on these servers to verify Apple's privacy promises.

I followed below url for converting Llama-3.1-8B-Instruct model but always fails even i have 64GB of free space after downloading model from huggingface. https://machinelearning.apple.com/research/core-ml-on-device-llama Also tried with other models Llama-3.1-1B-Instruct & Llama-3.1-3B-Instruct models those are converted but while doing performance test in xcode fails for all compunits. Is there any source code to run llama models in ios app.