All entries

ci: Bump CUDA Windows x64 builds to 13.4.1 (#28930) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47583571 macOS/iOS: macOS Apple Silicon (arm64) macOS Ap

metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) (#28599) metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) MiniCPM3 sets attention.key_length to 96 and does not set attention.value_length, whi

opencl: add generic ssm_scan (#28881) opencl: add generic ssm_scan opencl: fix whitespace Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47601188 macOS/iOS

OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv

vulkan: support sparse Flash Attention (#28105) vulkan: add sparse Flash Attention support for DSV4/GLM tune implementation add tests avoid nondeterministic atomicAdd add cm2 decode vector support sim

models : move build_arch_graph() after graph() template specialization (#28934) Move build_arch_graph()'s function definitions after the graph and graph template specializations have been explicitly d

cuda: support row-contiguous SUM_ROWS (#26308) cuda: support row-contiguous SUM_ROWS organize the code and add GGML_OP_MEAN to support row-contiguous tensors using the same shared kernel, and add a te

rpc : hash-cache only weights (#28789) rpc : hash-cache only weights ggml_backend_rpc_buffer_set_tensor and ggml_backend_rpc_set_tensor_async hashed every transfer above HASH_THRESHOLD and let rpc-ser

opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (#27637) opencl: gate the prebuilt q4_0 MoE GEMM on routing count opencl: stop writing zeros into the padded MoE activat

HIP: Enable AllReduce for ROCm (#27825) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47762387 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon

hex-cpy: use dma if src and dst are contiguous (#28906) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47770889 macOS/iOS: macOS Apple Silicon (arm64) macO

hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run (#28886) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47775478 macOS/iOS: mac

arXiv:2609.15702v1 Announce Type: new Abstract: Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is oft

arXiv:2501.03008v2 Announce Type: replace-cross Abstract: Context-aware machine translation can expose the evidence needed for pronoun choice, but standard fine-tuning does not explicitly prioritize t

arXiv:2609.15248v1 Announce Type: new Abstract: A learner probes at most k of n arms each round, receives the maximum of their rewards in [0,1], and competes with the best fixed arm. When does the pro

Banger paper from Google on agent harnesses for long-horizon tasks. (bookmark it) Google Research built a many-agent harness for long mathematical proofs, and it produced new results on open problems

arXiv:2609.13869v1 Announce Type: cross Abstract: Automatic sentence function identification is important for many downstream natural language processing (NLP) applications such as dialogue systems, t

arXiv:2512.24999v2 Announce Type: replace-cross Abstract: In this work, we introduce extit{basic inequalities} for first-order iterative optimization algorithms, forming a simple yet versatile framewo

arXiv:2609.14724v1 Announce Type: new Abstract: Inferring intelligence from observable behavior is a foundational challenge in artificial intelligence. We develop a theory of Bayesian intelligence for

arXiv:2609.15555v1 Announce Type: new Abstract: Bayesian optimisation (BO) typically relies on a single global Gaussian process (GP) model as its surrogate model. However, GP regression has cubic comp

arXiv:2609.14262v1 Announce Type: new Abstract: Joint source localization and geoacoustic inversion requires optimizing an objective built from an expensive normal mode propagation model. Bayesian opt

arXiv:2609.13264v1 Announce Type: cross Abstract: Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In additio

arXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers

arXiv:2609.14806v1 Announce Type: new Abstract: Reliable online autonomy is critical for quadrotor operation in urban airspaces, where global navigation satellite systems (GNSS) measurements suffer fr

arXiv:2609.15987v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy

arXiv:2609.15726v1 Announce Type: cross Abstract: Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not conver

arXiv:2609.15669v1 Announce Type: cross Abstract: Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures of

arXiv:2609.13819v1 Announce Type: new Abstract: Solving inverse problems with differentiable physics simulators holds the potential to revolutionize scientific discovery and engineering design, as it

So I would like to run qwen 3.8 27b locally for my ai agents, maybe even in parallel with other small LLMs (such as qwen3.5 9b, oss 20b etc..). What is the best hardware to do this? Not a video card b

Cloud outages can range from global service disruptions to issues isolated to a specific region, zone, or even just your project, workload or application. If you suspect a Google Cloud Platform outage

arXiv:2609.15706v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean

arXiv:2609.15624v1 Announce Type: cross Abstract: Researchers assessing competent generative-AI use at work must choose among self-reports, objective tests, and measures of oversight and reliance. We

arXiv:2609.14748v1 Announce Type: new Abstract: Road tunnels remove satellite visibility where connected and automated vehicles still require continuous, attributable, and integrity-bounded positionin

arXiv:2609.14995v1 Announce Type: new Abstract: The same task and compute budget can require different reasoning policies when evidence arrives in a different order. Early computation has more time to

arXiv:2609.12606v2 Announce Type: replace Abstract: While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructi

arXiv:2609.14352v1 Announce Type: new Abstract: AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document

arXiv:2609.15527v1 Announce Type: new Abstract: The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on c

arXiv:2609.15087v1 Announce Type: cross Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-wo

arXiv:2609.13815v1 Announce Type: new Abstract: Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images s

arXiv:2609.13345v1 Announce Type: cross Abstract: Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across

arXiv:2504.01157v1 Announce Type: cross Abstract: Knowledge-intensive analytical applications retrieve context from both structured tabular data and unstructured, text-free documents for effective dec

arXiv:2609.15517v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) pose a dual-surface safety challenge: both intermediate reasoning traces and final answers can contain harmful content. Ex

arXiv:2609.14512v1 Announce Type: new Abstract: Virtual worlds now host classrooms, meetings, conferences, shops, and social venues, and nearly every interaction they expose assumes a user who can sca

arXiv:2609.15940v1 Announce Type: new Abstract: Vision-language-action policies are typically evaluated one perturbation at a time, providing a useful diagnosis of their sensitivity to individual dist

arXiv:2503.00389v2 Announce Type: replace-cross Abstract: We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals.

arXiv:2609.14185v1 Announce Type: cross Abstract: Bird's Eye View (BEV)-based multi-view 3D object detection suffers from challenges of computational complexity, multi-scale feature extraction, and ef