Apple MLX
Timeline (last 90 days)
The authors provide a pip-installable package containing fused CUDA kernels (implemented via torch.cuda.jiterator, requiring no CUDA toolkit) and Apple MLX kernels, tested under fp32, fp64, fp16 and bf16.
Phonon is the name of an engine/component internal to Ollama used to carry speech capabilities, loaded and scheduled by mlxrunner (a model runner based on the Apple MLX framework); it is not a publicly known third-party speech model brand.
mlxrunner is Ollama's inference execution layer for Apple Silicon, relying on Apple's MLX array/neural network framework underneath and optimized specifically for the unified memory architecture.
The inference engines supported by Muse Spark Open include SGLang, vLLM, TensorRT-LLM, Hugging Face Transformers, Apple MLX, llama.cpp and Unsloth.
All Facts (4)
Phonon is the name of an engine/component internal to Ollama used to carry speech capabilities, loaded and scheduled by mlxrunner (a model runner based on the Apple MLX framework); it is not a publicly known third-party speech model brand.
50%Unverifiedmlxrunner is Ollama's inference execution layer for Apple Silicon, relying on Apple's MLX array/neural network framework underneath and optimized specifically for the unified memory architecture.
50%UnverifiedThe inference engines supported by Muse Spark Open include SGLang, vLLM, TensorRT-LLM, Hugging Face Transformers, Apple MLX, llama.cpp and Unsloth.
50%UnverifiedThe authors provide a pip-installable package containing fused CUDA kernels (implemented via torch.cuda.jiterator, requiring no CUDA toolkit) and Apple MLX kernels, tested under fp32, fp64, fp16 and bf16.
50%