Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

b12135

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.

b12136

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.

b12137

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.

b12138

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.

b12140

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.

b12141

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.

b12142

A fix was implemented to verify the combined K+V f16 scratch size in the Flash Attention dequantization path for Vulkan, addressing issue #30048.

b12143

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.

b12144

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.

b12170

The llama.cpp v1.21.70 release includes enhancements to the moe-cache system, introducing an LRFU/MQ-inspired hybrid cache with improved token handling, key computation, and decay calculations. Changes include adjusting the half-life parameter, increasing the number of classes to 8, refining score computation based on age, removing redundant branches, and improving documentation around unused slots and sorting. The release also features updated build binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with support for CUDA, Vulkan, ROCm, OpenVINO, SYCL, and other backends.

b12172

The update introduces batched tensor functions `get_tensor_n` and `set_tensor_n` for WebGPU, along with fixes for the editor-config checker and removal of an outdated comment.

b12174

The llama.cpp release b12174 introduces the ability to generate RC files directly without requiring a win-app.rc.in file, alongside a comprehensive set of precompiled binaries for macOS, Linux, Windows, Android, and openEuler across various architectures and backends including CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific hardware. The release also includes a standalone UI package.

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google DeepMind has launched Gemini Omni 1.2 Flash, introducing native 15-second video generation, improved reference adherence, stronger consistency across frames, multi-turn conversational editing, more natural speech, and cinematic camera movements. The model is now generally available via the Gemini API and Gemini for business, priced at $0.07 per second for 720p video—30% lower than its predecessor. It supports scalable workflows, including draft generation at lower resolutions, iterative edits, and upscaling to 1080p or 4K. Use cases include product explainers, social ads, virtual try-ons, and branded content, with applications across Google AI Studio, Google Cloud, Google Vids, Flow, the Gemini app, and Google Ads.

b12114

Fixed get_max_size to return maxBufferSize and improved the memset shader to handle buffer sizes exceeding the maximum binding size, preventing issues with whole-buffer bindings in memset and clear operations.

b12116

The llama.cpp release b12116 introduces support for the drama-3 text-to-speech model, includes cleanup improvements, and ensures the drama3 helper stops at the codebook tower limit. This update provides binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS, with support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, and SYCL. Some builds remain disabled or require additional setup.

b12118

The update enhances OpenCL performance for decode operations by optimizing workgroup usage for q4_K gate up and GLU, and adds support for Flash Attention (FA) in various configurations including GQA 2, 6, and 16 with different head sizes, improving efficiency on specific hardware setups.

b12121

A fix was implemented in llama.cpp to correct the calculation of on-device sequence state copy sizes for quantized key-value (KV) caches, ensuring accurate copying of data blocks and preventing crashes or incorrect state restoration. The update adjusts the element count computation using proper block size handling and removes redundant code elements.

b12122

The update introduces optimizations for CUDA by fusing NVFP4 gate/up operations and GLU within MMQ, honoring requested precision in fused gate/up MMQ, sharing scale checks for NVFP4, skipping unused FP4 kernels, testing with W4A8 configurations without scales and with batching, and adding checks for gate_scale before loading fused NVFP4 gate scale.

b12123

The update introduces DSV4_HC_PRE and DSV4_HC_POST support for OpenCL, along with improvements to dsv4_hc_post functionality, enhancing performance and compatibility across various platforms including macOS, Linux, Windows, Android, and embedded systems.

b12124

The release includes support for non-contiguous sigmoid operations in OpenCL, enhancing compatibility and performance across various hardware platforms. This update is part of a broader set of improvements and new binary distributions for multiple operating systems and backends, including macOS, Linux, Windows, Android, and openEuler, with support for CUDA, Vulkan, ROCm, OpenVINO, SYCL, and other accelerators.