Search headlines, summaries and articles to connect the dots.
A fix has been implemented to prevent crashes in the command-line interface when encountering invalid UTF-8 in prompts or files, with assistance from Claude. This update is part of the b12177 release of llama.cpp, which includes various binary distributions for macOS, Linux, Windows, Android, and other platforms.
The update introduces support for 3D convolution (conv_3d) on Hexagon hardware by generalizing the existing conv_2d implementation. It leverages the HMX tiled path, folds kernel dimensions into a virtual row, and uses a shared solver with an is3d flag. The host computes unfold divisors to avoid device-side division, prevents DMA queue overflow, and improves tile size selection based on VTCM usage. Additional changes include handling arbitrary positive strides, preserving load/shuffle paths for small strides, and fixing compiler warnings.
The release adds the Kimi-K3.1-Pro text model to llama.cpp, replacing full-attention MLA layers in K3 with DSA (Dynamic Sparse Attention) layers featuring a lightning indexer. The indexer uses an additive mask over the cache and reuses sparse flash attention paths, while preserving existing KDA layers and MoE components. The model's architecture includes four indexer tensors per DSA layer, hybrid memory for caching, and maintains quantization integrity by excluding indexer parameters from quant overrides. Verified against HF checkpoint with identical PPL beyond context length, and supports multiple platforms including macOS, Linux, Windows, Android, and iOS.
The latest release of llama.cpp (v1.2182) includes a change to raise the compute view limit for buffers with few tensors in the meta backend, along with reverting the deepseek41 test model back to a 6-layer configuration. The release provides precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS, supporting various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific hardware. Some openEuler builds remain disabled.
The release includes the addition of arange functionality for OpenCL, enhancing support for array operations in the OpenCL backend. This update is part of a broader set of improvements and compatibility fixes across multiple platforms, including macOS, Linux, Windows, Android, and various GPU and NPU backends.
The llama.cpp release b12184 includes a fix to add a missing link to pthread and privately link Threads::Threads, addressing potential runtime issues. The release provides precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific hardware. Additional UI components are also available.
A fix for shared memory bank conflicts in the lightning indexer has been implemented for CUDA support in llama.cpp version b12185, improving performance and stability on CUDA-enabled devices.
A change has been made to add the 'readonly' attribute to decodeBuf declarations in the Vulkan backend, with potential performance improvements expected in future driver versions.
The latest release of llama.cpp (b12187) includes the implementation of a WebGPU group norm kernel, with associated CI workflows, performance tests, and cleanup of related code. The update supports various platforms including macOS, Linux, Windows, Android, and specific hardware backends like Vulkan, CUDA, ROCm, OpenVINO, SYCL, and Snapdragon devices. Some builds remain disabled or experimental.
The server update addresses slot processing order by ensuring parent slots are visited before child slots, preventing delays caused by child tasks landing on lower slot IDs. This change ensures all child tasks join the same batch after being woken by their parent. Additionally, new test tags have been introduced for monitoring: __TEST_TAG_WAIT_PARENT_SLOT__ for child slot waits, __TEST_TAG_PROMPT_CACHE_RESTORE__ for prompt cache restores, and __TEST_TAG_PROMPT_CACHE_FULL_RESTORE__ when a cached prompt is fully contained in a new one based on token counts.
The metal backend's kernel_group_norm_f32 was updated to correctly handle tensors with ne03 > 1 and non-contiguous inputs by dispatching one threadgroup per (group, i03) pair, computing per-batch statistics, clamping group element count for incomplete groups, and supporting strided access via separate strides for source and destination. The fix also restricts GROUP_NORM to f32 inputs and improves performance through specialized pipeline variants.
Run Claude Code as a remote agent on Amazon Bedrock AgentCore. Each coding task runs in its own isolated session in your AWS account, every model call goes through Amazon Bedrock, and the result comes back as a GitHub pull request you review and merge.
Greenlight Financial resolves more than 90% of up to 4,000 monthly security and risk cases without human intervention using Luna, a tiered multi-agent system on Amazon Bedrock AgentCore. This post covers the architecture, episodic memory for continuous learning, and the expansion from SOC operations into financial risk triage.
A year ago, NVIDIA open sourced its Aerial wireless software, joining Sionna and a broader suite of open source tools for accelerating next-generation 6G network development. Together, they give researchers a foundation for testing ideas, comparing results and building on each other’s work — connecting simulation and AI training with experiments on real over-the-air wireless […]
A laser scientist reviews the laser light cannon from the Steven Universe cartoon, including its highly unusual beam shape.
Around 7PM each weeknight, I find myself standing in front of the fridge, trying to decide on something for dinner that won't make my husband complain, "Chicken again?" Yes, I should meal plan more, but I don't, so this is where I'm at. A nightly battle in which the chicken usually wins. Recently, my best […]
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator. This post shows how two optional API fields place one model per partition, and what we measured against a whole older GPU.
Learn how to build a serverless Model Context Protocol (MCP) server on Amazon ECS with AWS Fargate that gives AI agents secure, metadata-driven access to an enterprise data lake. Exposing a new dataset requires only a JSON file, with no per-dataset integration code.
An approach of taking many photos to enhance one final image is a technique called "stacking". Stacking alone doesn't account for everything so this is a take that helps get better alignment of images, allows comparisons, and drop bad images that dont match. Its not super resolution but it feels like when you look at it. it reduces the noise and makes it look more organic shot with less expensive hardware. enjoy! Comments URL: https://news.ycombinator.com/item?id=50401218 Points: 1 # Comments: 0
Article URL: https://github.com/zero11-0203/s3mail Comments URL: https://news.ycombinator.com/item?id=50401533 Points: 1 # Comments: 0
