The latest release of llama.cpp, version b12132, includes the removal of u8path() in favor of generic_string(), along with updated binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The latest release of llama.cpp (b12135) introduces support for MEAN operations in WebGPU, enhancing performance and functionality across multiple platforms including macOS, Linux, Windows, Android, and iOS. The release includes precompiled binaries for various architectures and backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and zDNN, with specific builds for Apple Silicon, Snapdragon devices, and openEuler systems. Some features remain disabled or are under development.
The update addresses an issue in llama.cpp where the number of GPU layers was incorrectly calculated by not accounting for skipped NextN layers, leading to improper layer distribution between CPU and GPU. The fix ensures that skipped NextN layers are included in the n_gpu_layers count and properly assigned during model loading, resolving a bug where layer 0 remained on the CPU despite offloading all other layers.
A recent update to llama.cpp addresses a critical issue by rejecting non-object session updates in the server, preventing malformed realtime session data from causing uncaught exceptions and server termination. The release includes binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS, with support for various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The update introduces optimized Metal kernel usage for matrix multiplication with K values between 32 and 64, and adds a new kernel for BF16 x BF16 matrix multiplication, improving performance on Apple Silicon devices.
The latest update to llama.cpp (v1.2140) adds support for the `truncate=false` parameter in YaRN, enabling more accurate frequency interpolation for models like gpt-oss and certain PLaMo-3 variants by preserving non-integer interval boundaries. The change includes updates to GGML operations and CPU backend handling, with CUDA backend support, new tests, and refactoring of RoPE helpers into internal headers. Default behavior remains `truncate=true` for backward compatibility.
The latest update to llama.cpp introduces reference-counted checkpoints instead of deep-copies, reducing memory overhead and improving efficiency. This change adapts the slot save/restore checkpoint mechanism to shared_ptr checkpoint lists and common_state_data buffers, with contributions from multiple developers and AI assistants.
A fix was implemented to verify the combined K+V f16 scratch size in the Flash Attention dequantization path for Vulkan, addressing issue #30048.
The Vulkan implementation of the Fast Walsh-Hadamard Transform (FWHT) has been enhanced to support block widths up to 8192, using shared-memory shaders for larger blocks, and now includes F16 input capability via shader-float16, with pipelines created only when device limits allow. This update aligns Vulkan with CUDA's capabilities and improves efficiency by eliminating the need for F32-to-F16 conversions.
The update introduces CUDA optimizations including linearizing the mixture-of-experts (MoE) data layout for MMQ/MMF, applying tile size optimizations more broadly, and addressing a half-precision (F16) performance regression.
