Core Ml
PulseAugur coverage of Core Ml — every cluster mentioning Core Ml across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Developer builds local ML pipeline to block risky code commits
A recent computer science graduate has developed a local machine learning pipeline designed to prevent risky code commits before they are pushed. The pipeline integrates three layers of checks: a Rust regex pass for kno…
-
ANEForge enables direct Python programming of Apple Neural Engine
A new Python package called ANEForge allows developers to directly program the Apple Neural Engine (ANE) without relying on CoreML. This bypass enables more efficient use of the ANE, which is the dedicated neural accele…
-
iOS 27 Siri integrates WaveRNN and FastSpeech2 models
Siri on iOS 27 is reportedly utilizing WaveRNN and FastSpeech2 models, discovered within the simulator's files. These models are integrated in an espresso format, suggesting an optimized deployment for on-device process…
-
Apple unveils CoreAI for on-device inference on Apple Silicon
Apple has introduced CoreAI, a new on-device inference engine designed to replace CoreML and offer an alternative to existing frameworks like MLX and llama.cpp. This engine is optimized for Apple Silicon, particularly f…
-
iPhone LLM benchmark: Neural Engine beats GPU in sustained performance
On-device LLM performance on the iPhone 17 Pro reveals that while GPUs offer superior initial generation speeds, they quickly overheat and throttle. Apple's Neural Engine, though slower to start, maintains a more consis…
-
MLX, LiteRT-LM, and CoreML benchmarked for iPhone LLM performance
A recent benchmark tested four on-device LLM runtimes on an iPhone 17 Pro, comparing decode speed and memory usage. MLX emerged as the fastest for general-purpose models like Qwen 3.5 2B, while LiteRT-LM excelled specif…
-
SDXL image generation now works on iPhone via Off Grid app
The open-source app Off Grid, which enables on-device AI image generation, has fixed a bug that prevented SDXL models from running on iPhones. The issue stemmed from the app's validation code only recognizing a monolith…
-
Claude Code reviews iOS app performance, suggests code fixes
An iOS developer used Anthropic's Claude Code to review their app, HerdCount, for performance issues. The AI identified and suggested fixes for several problems, including inefficient image rendering, main thread blocki…
-
AI model predicts stuttering events from audio, deploys on-device
Researchers have developed a new Convolutional Neural Network (CNN) model capable of predicting upcoming stuttering events from short audio clips. The 616K-parameter model, trained on the SEP-28k dataset, demonstrates a…