b12493
The update enables the fast implicit GEMM path for F32 kernels in CUDA, previously limited to F16, by converting input data to F16 in a pool buffer and using F32 accumulation, significantly improving performance for large channel counts.
Official announcements and industry reporting. Follow the timeline of AI.
From the latest news to tools that work for you.
OpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首A
AI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首KKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首M
MemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首EEvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首JJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首MMy Glow Up AI provides free analysis based on selfies, without requiring registration, and can generate hairstyle recommendations and beauty plans that suit you.
待评分 · 分类列表推荐E
ElicitKnowledge & researchElicit provides semantic search, research report generation, literature screening, and data extraction for scientific research. It enables traceable answers within source materials and organizes evidence through a literature library, research agents, and ongoing tracking workflows, making it ideal for advancing from initial problem exploration to systematic reviews.
待评分 · 分类列表推荐ZZoom Workplace is Zoom’s team collaboration platform, integrating video conferencing, chat, calendars, and documents, and leveraging built-in AI to organize discussions, draft messages, and track follow-up tasks.
待评分 · 分类列表推荐MMeta's free AI chat assistant
待评分 · 分类列表推荐The update enables the fast implicit GEMM path for F32 kernels in CUDA, previously limited to F16, by converting input data to F16 in a pool buffer and using F32 accumulation, significantly improving performance for large channel counts.
A fix has been implemented to return a 400 error when both grammar and ignore_eos parameters are enabled in the server, preventing crashes and improving validation by moving the check into the sampler. Redundant tests have also been removed.
The Llama UI design system, including tokens, surfaces, fonts, and base components, has been moved from a temporary repository to ui/lib/ui, where it is now published as @ggml-org/llama-ui. Llama Chat now imports all UI elements—including model components, constants, enums, and helpers—from this centralized library, eliminating duplicate code. The update includes updated branding with Llama Sans and Llama Mono fonts, improved submenu rendering, enhanced elevation for chat form elements, and integration with the llama-brand package for colors and logo. The UI is now consistently applied across the application, with builds and deployment configurations adjusted accordingly.
The Llama Chat UI has been upgraded to SvelteKit 3, integrating its built-in service worker for improved update detection and offline functionality. The migration includes updates to Vite 8, TypeScript 6, Storybook 10, and ESLint 10, along with the replacement of deprecated packages and resolution of npm audit issues through dependency overrides, including pinning minimatch to version 11.0.5 to address a security vulnerability. Changes also align with current Svelte patterns, such as using $state instead of stores and adopting new syntax for actions and class bindings.
The llama.cpp release b12474 introduces the application of output projection weight scale and provides precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various backends such as CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The update addresses three issues in the OpenCL implementation of the bin flash-attention prefill path: releasing a previously unreleased WMM flash-attention mask fallback image, excluding q8_0 K/V at head size 512 from the WMM kernel due to incorrect results, and preventing the use of the WMM path beyond device 3D image limits to avoid clCreateImage failures.
The web UI for Llama.cpp has been relocated from tools/ui to ui/apps/chat as part of a structural refactoring to separate the component library (ui/lib) from the applications built on it. The app is now officially named Llama Chat, with its package renamed to @ggml-org/llama-chat, while maintaining private status. Documentation, help text, comments, and other references have been updated to reflect the new name, though legacy identifiers remain unchanged for backward compatibility.
Agentic workloads, long documents, and large codebases are pushing context lengths from tens of thousands of tokens to hundreds of thousands. At those lengths,...
Quantum processors are being integrated into supercomputing centers worldwide. National programs in North America, Europe, and Asia are driving the installation...
The update introduces support for split_k in conv3d operations using Vulkan, leveraging a 256x128 shape (coopmat2-only) when beneficial and reusing the mul_mat split_k reduce shader.
PyTorch Foundation Ambassadors bring people together to learn, share technical knowledge and contribute to PyTorch Foundation projects and the wider open-source AI ecosystem. In this November roundup, we highlight some... The post PyTorch Foundation Ambassador Community Highlights November 2026 appeared first on PyTorch.
The release includes support for json sort_keys=true in jinja, with various precompiled binaries available for macOS, Linux, Windows, Android, and other platforms, including CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon backend options.
A fix was implemented to prevent the MUL_MAT_ID operation from aborting on AMD devices when using F32, F16, or BF16 data types with an odd number of columns in src0, particularly affecting rank 1 LoRA on MoE expert weights. The issue arose because MMVF read src0 in pairs and required an even ne[0], so the fix restricts MMVF usage to cases with even ne[0], defaulting to fallback for other shapes. This resolves issue #30576.
A performance improvement in llama.cpp addresses the issue of an O(n_cells) scan during each sequence removal, optimizing efficiency by reducing computational overhead.
The update addresses issues with reasoning effort levels by ensuring rejected levels are properly handled during parsing, preventing 500 errors on API endpoints. It maintains support for template-ignored levels and aliases while trimming the output_config.effort test to a single level.
arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship on-device, Phi-3-mini, Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, and Gemma-2-2B-Instruct, typically at 4-bit precision, sit outside this evidence base. We present a reproducible one-GPU audit of four detectors spanning three paradigms: length-normalized token-margin calibration, a lexical n-gram baseline, and two sampling-based consistency methods (semantic entropy and SelfCheckGPT-NLI) on two small open instruction-tuned models (Llama-3.2-3B-Instruct and Qwen2.5-3B-Instruct) loaded at 4-bit NF4 quantization on a single Colab T4 GPU, evaluated on closed-book TriviaQA. Cross-model ranking transfer is poor: Spearman rho is -0.80 and Kendall tau-b is -0.667, meaning the detector ranking actively inverts between the two models, and the cheap lexical baseline is statistically indistinguishable from the sampling-based consistency detectors on both models under bootstrap 95 percent confidence intervals. As a second, methodological contribution, we show that the standard token-overlap-to-multiple-choice correctness labeler for TruthfulQA-Generation produces near-chance AUROC (0.46-0.59) for all four detectors on both models, a labeler failure, not a detector failure, since the same detectors reach 0.69-0.89 AUROC on TriviaQA under the identical pipeline. We release the harness, prompts, and per-item scores and frame the detector choice explicitly as a fairness-of-error-rates allocation problem for practitioners deploying on resource-constrained, on-device hardware.
The update includes the addition of four missing features in jinja, along with applied suggestions and a fix for an error message. This release is part of the llama.cpp project, offering binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The llama.cpp release b12421 includes updated binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS, with support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon. The documentation has been reorganized, moving per-model TTS content to /docs and linking it from other pages. Some builds, like macOS Apple Silicon with KleidiAI and openEuler variants, are currently disabled.
The update introduces a change to the template soft_max_f32_parallelize_cols_single_row to store column elements in registers when feasible, reducing global memory traffic from five passes to two, thereby improving performance on CUDA-enabled systems.
The qwen2vl model in llama.cpp was producing incorrect results due to NULL values being passed for FFN weight scales, preventing per-tensor NVFP4 scales from being applied. This issue has been resolved by correctly passing the scales to the build_ffn function, consistent with how qwen2 handles them.
Give your curiosity direction. Make every day of reading count.