The Llama.cpp project has released an update that includes new get/set tensor 2D functions for Vulkan, enhancing its backend capabilities. This release also features updates to the ggml-metal interface and support for various operating systems, including macOS, Linux, Android, and Windows, with specific configurations for Apple Silicon and CUDA. The addition of these functions aims to improve performance and usability for developers working with tensor operations in Vulkan. Overall, this update reflects ongoing enhancements in the Llama.cpp project to support a wider range of hardware and software environments.
Read originalThe latest version b8991 of llama.cpp has been released, featuring updates for various operating systems.
The latest update to llama-mmap improves compatibility with various platforms and model sizes. Key enhancements include support for 32-bit wasm and updates to gguf.cpp style.
The v0.18.2rc0 release includes a fix for handling the max_pixels parameter in the PaddleOCR-VL image processor across transformations.
© Lev SelectorAnthropic has released a suite of plugins that enhance the Claude ecosystem.
The ggml-webgpu project has introduced an upscale shader with multiple implementations. This update supports various platforms including macOS, Linux, Android, and Windows.