Models & Labs
Ollama MLX Boosts Apple Silicon Performance
Ollama Bloghigh confidence
Why it matters
- →Enhances AI model performance on consumer hardware like Apple Silicon.
- →Improves model portability between datacenter and desktop environments.
- →Increases processing speed and efficiency, benefiting developers and users.
Ollama has updated its MLX engine to achieve its highest performance yet on Apple Silicon. By utilizing Apple's unified memory and the Metal-backed MLX framework, the engine now delivers faster and more efficient model outputs. The update introduces support for NVIDIA's NVFP4 format, enhancing output quality while maintaining performance. Additionally, new optimizations have increased processing speed by 20%, and a snapshot system improves responsiveness in agent workflows. This update enhances the portability and efficiency of AI models on consumer hardware.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.