Search headlines, summaries and articles to connect the dots.
The fix addresses intermittent CI failures in TOPK_MOE tests caused by near ties in logits, particularly with uniform random inputs and narrow-range gating functions like sqrt_softplus. The solution involves redrawing logits until group selection and top-k decisions have a relative margin of 1e-4 in double precision, and constructing logits by inverting the gating function using a grid-based approach to ensure consistent expert selection across backends.
The startup Aina bets you won’t need to rely on your phone to control virtual assistants. It’s making a smart ring that lets you control the actions of your autonomous agents with one tap.
Maximum inner product search (MIPS) sits at the core of recommendation systems, search, and retrieval-augmented generation (RAG). Given a query vector, MIPS systems search within a database of millions of candidate key vectors for the one that best matches the query. The original data point associated with that best-matching key is then used to handle the query: in RAG, the document that is best suited to answer the question is typically prefixed to the query. As the number of keys grows to millions and vector dimensions reach thousands, the computational cost of running an exhaustive…
Article URL: https://github.com/ag3ntsc4rn/autorun-audit Comments URL: https://news.ycombinator.com/item?id=50374018 Points: 1 # Comments: 0
Article URL: https://github.com/akshit-bansal11/edgepad Comments URL: https://news.ycombinator.com/item?id=50374433 Points: 1 # Comments: 1
Article URL: https://github.com/sooftware/lmux Comments URL: https://news.ycombinator.com/item?id=50378582 Points: 2 # Comments: 0
Article URL: https://github.com/rib3ye/oldTunes Comments URL: https://news.ycombinator.com/item?id=50380614 Points: 1 # Comments: 0
Some agent-evaluation questions are narrow and repeatable, and decision models answer exactly that kind of question. This post shows how to connect two decision models, Jev and Strands Decider, to Amazon Bedrock AgentCore Evaluations through code-based evaluators, and how to validate a decision-model check before you gate a release on it.
Optimized TOP_K performance on Hexagon backend by skipping bitonic sort for tiles whose maximum cannot surpass the k-th best value, replacing tile sort with top_k_scan() to reduce 256-float blocks using HVX max-reduce, and inserting only surviving elements into a sorted k-entry list. Supports k values from 2 to 64 and row widths over 1024 in both single-row and multi-row paths. NaN treated as -INF, ties preserve first-seen index. Eliminated scalar reads from VTCM in hex-top-k.
The update introduces the TOP_K_MASK operation for Hexagon, simplifying the kernel and eliminating redundant host configuration.
The llama.cpp release b12098 includes accurate support for Qwen3-VL video prompt format and provides precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with various backend options such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific optimizations. The release also features a standalone UI package and detailed setup guides for specific hardware configurations.
The update introduces initial support for the LIGHTNING_INDEXER operation in the Hexagon backend, including optimizations for HMX prefill, q4_0 and f32 K support, pipelined HMX paths, improved DMA pipeline with canonical double buffering, and enhanced kernel parameter alignment. It also adds options to force HMX/HVX execution paths and supports dimension collapse.
The update resolves issues with -hf tag matching in longer quantization names, ensuring tags start at token boundaries. It also adds support for underscores as separators in quantization tags, improving compatibility with filenames like step3p5_flash_Q4_K_S-00001-of-00012.gguf.
The gguf writer now writes host-buffer tensor data directly to the file, skipping the temporary staging vector, which eliminates per-tensor allocation, zero-initialization, and memcpy operations.
The ggml library now checks view bounds based on the actual bytes reached by strides, improving accuracy for strided views. Views are required to start from contiguous elements along dimension 0, ensuring correct data access. Convolution windows in delta_net are created with all rows at once to prevent stride-related issues.
The llama.cpp release b12109 is now available, offering pre-compiled binaries for macOS, Linux, Windows, Android, and openEuler across various architectures and backends including CPU, CUDA, Vulkan, ROCm, OpenVINO, SYCL, and specialized hardware like Snapdragon. The release includes support for Apple Silicon and Intel macOS, multiple Linux distributions, and detailed setup guides for specific platforms.
The llama.cpp project has been updated to version 0.9.0, with new releases available for multiple platforms including macOS, Linux, Windows, Android, and iOS. The update includes support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific hardware. Some builds are marked as disabled or experimental, and detailed setup guides are provided for specific configurations.
Article URL: https://github.com/biolend83/tubehaus Comments URL: https://news.ycombinator.com/item?id=50363507 Points: 1 # Comments: 0
kv-cache : never return 0 kv_rows for sequences without cells (#31570) A cache that shares the cells of another one (f.ex. the gemma4 assistant) can build a graph before its sequences have any cells, f.ex. at the server warmup. get_n_kv_rows() then returned 0, which means that kv_rows are not used, so the graph fell back to the dense KQ mask and the scheduler re-planned for it. Later graphs with larger masks then aborted with GGML_SCHED_DEBUG_REALLOC=1. **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12065/llama-b12065-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/l
Author: Li Shuiqing | Editor: Xin Yuan — According to Zhidongxi (WeChat official account: zhidxcom), on October 31, Alibaba announced a partnership with Apple to integrate Qwen into Apple Intelligence. Chinese users will be able to directly access Qwen’s capabilities for text and image understanding, content generation, and more, within Siri, writing tools, and visual intelligence features. These functions will begin beta testing starting November 4 alongside the latest iOS Developer Beta version, and...
