b12438
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.
Official announcements and industry reporting. Follow the timeline of AI.
From the latest news to tools that work for you.
EvoMap 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A
AI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
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OOpenDesign 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CClipdrop is a suite of AI-powered image creation and editing tools, covering background removal, local cleanup, image enlargement, upscaling, relighting, text removal, and background replacement. It allows users to process images directly in the browser and also provides developers with an API for integrating these capabilities into their applications.
待评分 · 分类列表推荐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AAssemblyAI is a speech AI platform for developers, offering pre-recorded, real-time, and short-form synchronous transcription APIs. It enables the building of voice-based applications by integrating capabilities such as speaker identification, emotion analysis, chapter and summary extraction, as well as speech agent functionality, dictation, and sensitive information processing.
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.
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.
Prefix caching helps coding agents stay fast as conversations grow. Prompts, tool calls, and inference routing determine how much work the model can reuse.
A fix has been implemented to correct the placement of begin/end of image tokens in the Inkling 2 model within the chat functionality, along with the addition of a test to ensure stability.
The release includes a fix to clear the slot cache when the global LoRA configuration changes, ensuring consistency in model loading and inference. Prebuilt binaries are available for multiple platforms including macOS, Linux, Windows, Android, and iOS, supporting various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The latest release of llama.cpp introduces support for Inkling 2, including text and vision capabilities. This update includes text inference implementation, GGUF conversion for text models, vision multimodal projection support, still-image encoding, flash attention with folded bias and sinks, and improvements to tensor mapping and testing. The changes also address model conversion, checkpoint handling, and compatibility across multiple platforms, with support for CPU, GPU (CUDA, ROCm, Vulkan), and specialized hardware like Snapdragon and OpenVINO.
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.
The update refactors DFlash-based speculative decoding methods in llama.cpp by restructuring code organization, sharing components across models, splitting decoder graphs per head, and introducing dedicated classes for DFlash2 and LiliCorr drafts. It also adds support for new draft types, improves documentation, and removes unused code.
Imaging black holes is challenging because they are distant and appear tiny in the sky—for example, M87*’s observed ring spans just 42 microarcseconds. The...
Molecular dynamics (MD) is an indispensable tool across physics, chemistry, biology, and materials science. Owing to its arithmetic structure, particularly the...
A warning is now issued when the --spec-draft-p-min parameter is used with probabilistic draft sampling, as the draft's top probability does not reliably indicate how much of the draft the target model would accept under rejection sampling. The warning is skipped for drafters that do not use p_min, such as n-gram and DSpark.
The latest release of llama.cpp (b12362) includes optimizations for grammar matching through left factoring, improved handling of character class boundaries, prevention of infinite expansion, and enhanced code clarity with ASCII comments and deduplicated logic. It reverts prior changes related to AST refactoring and alternative limits, while introducing shared immutable rules and removing performance benchmarks. The release supports multiple platforms including macOS, Linux, Windows, Android, and iOS, with various backend options such as CUDA, Vulkan, ROCm, OpenVINO, and SYCL.
The llama.cpp project has released version 1.0.0, marking a significant milestone with numerous improvements across multiple platforms including CUDA, Vulkan, Metal, SYCL, OpenCL, and WebGPU. Key updates include enhanced support for quantized models (Q5_0, Q5_1, FP8), optimizations for flash attention and MoE caching, improved server security features like CORS protection and SSRF mitigation, UI enhancements such as sidebar reorganization and live-preview markdown editing, and better cross-platform compatibility. The release also includes bug fixes, CI/CD improvements, and updated dependencies.
The release includes support for Q5_0 and Q5_1 quantization levels on Hexagon NPUs, with dedicated kernels for Q5_0 in the hex-mm module.
A security update has been released to address Server-Side Request Forgery (SSRF) vulnerabilities related to CORS proxy and media URLs in the llama.cpp server component.
Human motion offers roboticists a great starting point for teaching humanoid robots how to move. A human demonstration captures the coordination and timing...
The update requires the position embedding tensor for HunyuanVL to be explicitly provided as F32 during model loading to prevent buffer overflow issues when using F64 tensors, ensuring compatibility and stability on first image requests.
Running a frontier-scale model locally means keeping all its weights in GPU memory; the largest models no longer fit on one machine. Two NVIDIA DGX Stations...
TL;DR Helion now uses compile-time heuristics that analyze a kernel’s IR and dataflow to pick fast settings without slow autotuning. It classifies the kernel as matmul, reduction, or pointwise and... The post Fast by Default: Compile-Time Heuristics for Helion Kernels appeared first on PyTorch.
Give your curiosity direction. Make every day of reading count.