Search headlines, summaries and articles to connect the dots.
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.
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.
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`get_tensor_n` and `set_tensor_n` for WebGPU, along with fixes for the editor-config checker and removal of an outdated comment.
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.
Article URL: https://github.com/AntidrawHQ/antidraw Comments URL: https://news.ycombinator.com/item?id=50391875 Points: 3 # Comments: 1
I built it to replace the repetitive workflows of moving tabs and copying indicators across many tools and tabs for every investigation. You use your own API keys, and functions like decoding, identifying commands, and man pages all run locally with no LLM.Please let me know what you think, you can try it here right now. More information about it can be found here: ceplang.org/start.htmlAs well as a short demo here: https://youtu.be/bzGGigpeiXg Comments URL: https://news.ycombinator.com/item?id=50391790 Points: 1 # Comments: 0
English isn’t my first language, sorry for grammar mistakes.I usually use Windows and Android, and these two platforms can be linked via Microsoft's "Link to Windows", or "Phone Link" program. So, you can easily use some features such as notifications, messages, screen mirroring, and clipboard synchronization on Windows from your Android phone.Recently, I changed my personal computer to macOS from Windows, and it made me need a similar program. I developed this program to run on macOS while still using the "Link to Windows" app on Android phone.It supports most features of the Windows client (notifications, messages, photos, mirroring, file transfer, etc.), except calling.The license is MIT. This project is an unofficial client unrelated to Microsoft and has no affiliation with them. Comments URL: https://news.ycombinator.com/item?id=50389540 Points: 1 # Comments: 0
Phonon, a small text-to-speech model that runs entirely on the user's device without requiring internet access, has been released with support for English, French, German, Spanish, and Portuguese. Built on the Pocket TTS lineage using flow matching, Phonon achieves high-quality audio in compact sizes (65 MB and 75 MB), with the 31m version licensed under Apache 2.0 for commercial use. It excels in intelligibility and speed, ranking first in German and Spanish on Hugging Face's Open TTS Leaderboard and leading in CPU streaming benchmarks. The model supports voice cloning, custom voices via Gradium Studio, and integrates with Hugging Face Transformers. It is available in multiple formats and backends, including WebAssembly, GPU, and NPU, enabling deployment across phones, laptops, single-board computers, and browsers. Over 200,000 downloads were recorded in its first two weeks, with active developer adoption through tools like ExecuTorch, Micdrop, and Spaces. Future developments include support for additional languages, smaller models, and custom vocabulary fine-tuning.
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.
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.
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.
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.
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.
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.
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.
The update enables f32 and q5_k multi-column GEMV by default for Adreno X2 on X2E devices, improving performance for specific computational tasks in the llama.cpp framework.
