b12114
Fixed get_max_size to return maxBufferSize and improved the memset shader to handle buffer sizes exceeding the maximum binding size, preventing issues with whole-buffer bindings in memset and clear operations.
Latest news
AI NEWS × FOXAIFind your next step
Explore AI tools From the latest news to tools that work for you.
Discover AI tools
Swipe to explore →M
MemoAIMusic & audio
AI ShortWriting & content
KiroCoding & development
Open DesignDesign & 3D
EvoMapAgents & automation
JAXModels & infrastructure
FinBusiness & support
Zoom WorkplaceOffice & productivity
ClipDropImages & editing
妙播Marketing & commerce
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AAI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首KKiroCoding & developmentKiro 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OOpen DesignDesign & 3DOpenDesign 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EEvoMapAgents & automationEvoMap 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JJAXModels & infrastructureJAX 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FFinBusiness & supportCLIENT-ORIENTED AI SMART BODY。
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CClipDropImages & editingClipdrop 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 · 分类列表推荐妙妙播Marketing & commerceTHE AI LIVE TELECOM SOLUTION FROM THE AD
待评分 · 分类列表推荐AI, as it happens
1171 published storiesCompute & infrastructure · 154 storiesClear filters ×
2026-11-05
Follow the timelineLiquidCP: Decoupling Attention Tasks from Communication and Kernel Boundaries in Context Parallelism
arXiv:2611.04401v1 Announce Type: new Abstract: Context parallelism (CP) partitions long sequences across GPUs for LLM training and inference. For variable-length training and full prefill, attention-balanced placement can leave token loads uneven, while ring execution repeats overhead at each computation and communication step. In stage-serialized decode CP (DCP), long-running tasks delay dependent work and leave substantial GPU hardware idle. We propose LiquidCP, which unifies training and inference through a common model of Transfer, Compute, and Reduction tasks with tile-level dependencies, decoupling attention tasks from communication and kernel boundaries. For training and full prefill, MegaRing incorporates BuddyRing placement to balance attention and token loads, and coalesces ready KV regions during forward attention to amortize overhead. For decoding and mixed batches, MegaDCP selects history-KV splits by jointly modeling the completion of attention and its dependent reductions. A shared persistent GPU-resident engine executes both designs. Compared with the fastest baseline per configuration on eight H100 GPUs, MegaRing achieves geometric-mean core-attention speedups of $1.23\times$ forward and $1.18\times$ backward, and accelerates a Transformer layer by $1.08$--$1.16\times$. MegaDCP achieves geometric-mean core-attention speedups of $1.20\times$ for decode-only and $1.35\times$ for mixed batches. In vLLM serving with KV prefix cache, it achieves an average time-to-first-token speedup of $1.22\times$.
NVIDIA CUDA 13.5 Brings NVIDIA Vera Rubin GA Support
As artificial intelligence and accelerated computing continue to push the boundaries of what's possible, the latest NVIDIA CUDA release arrives to unlock...
vLLM Delivers Day-0 Support for Kimi K3.1 Pro
vLLM supports Kimi K3.1 Pro on day 0: sparse attention on a KDA hybrid, a packed KV cache with FP8 or NVFP4 latents and MXFP4 index keys, token-sharded prefill, decode context parallelism, and fused low-latency decode.
2026-11-04
Follow the timelineAn entirely open-source AI code assistant inside your editor
Continue enables you to easily create your own coding assistant directly inside Visual Studio Code and JetBrains with open-source LLMs.
b12094
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.
b12096
The update introduces the TOP_K_MASK operation for Hexagon, simplifying the kernel and eliminating redundant host configuration.
b12098
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.
b12099
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.
b12100
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.
b12101
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.
b12102
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.
b12109
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.
b12110
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.
Fairway: Load-Aware KV Cache Reuse for LLM Prefill Scheduling
arXiv:2611.02082v1 Announce Type: new Abstract: LLM-based applications often employ agentic workflows and retrieval-augmented generation (RAG), which build long prompts from shared context. When prefixes are shared across requests, serving engines reuse the key-value (KV) cache to skip parts of the prefill computation. Reuse is typically graded: the uncached work of requests in a queue can differ by up to 100x. In this setting, the order of scheduling determines the time-to-first-token (TTFT) for the queued requests. KV reuse-first scheduling, which prioritizes the requests with the longest KV cache hit, gives the lowest median TTFT but starves expensive requests under load spikes; first-come-first-served (FCFS) scheduling bounds the tail but raises the median TTFT. We present Fairway, a prefill scheduler built on adaptive reuse prioritization: it favors KV cache reuse while queues are short, and shifts toward fair allocation as requests wait longer relative to their own prefill time. Fairway employs a virtual dual lane model: a KV reuse-first Fast lane and a Fair lane atop the serving engine's waiting queue that enables speeding up of cheap reuse requests without starving expensive ones. This model automatically adapts to the workload without any per-workload tuning. Fairway lowers the tail TTFT at no cost to the median in transient overload. Across workloads and load levels, Fairway matches or beats the best baseline, with a p99 TTFT up to 8.6x lower than prior prefix-aware schedulers. During load spikes, it keeps the tail of FCFS at a 6x lower median TTFT.
From Single-Shot QA to Continuous Perception: Revisiting the Energy Composition and Optimization Boundary of Edge VLMs
arXiv:2611.00036v1 Announce Type: new Abstract: Visual-prefill energy conclusions for edge vision-language models (VLMs) are commonly drawn under single-shot workloads; we revisit them under continuous perception. Profiling nine VLMs across three architecture families on Jetson AGX Thor and Orin (4,508 records, calibrated with a pure-text task), we find two mutually independent energy laws: the per-output-token decode cost grows monotonically with model scale, whereas the visual-prefill (image-encoding) cost is dominated by visual-encoder architectural efficiency, not scale. Under continuous perception ($N{=}10$) with sparse output, visual-prefill energy reaches 92--97\% of total. We derive optimization strategies---visual frame reuse, adaptive output truncation, task-aware routing, and encoder throughput optimization---for edge VLM deployment.
GC-MoE: Overlapping Expert-Parallel Token Dispatch with FP8/FP4 Grouped GEMM via CUDA Green Contexts
arXiv:2611.04222v1 Announce Type: new Abstract: Under expert parallelism, mixture-of-experts (MoE) layers pay all-to-all token dispatch, grouped GEMMs, and a combine step in every layer. In decode each rank holds only 1-256 tokens: dispatch latency and weight traffic dominate while tensor-core utilization is inherently low. In fused operators such as DeepGEMM's Mega MoE, dispatch and computation overlap only by sharing every SM: dispatch warps compete with TMA/MMA and epilogue warps for registers, shared memory, and issue slots; every phase shares one CTA resource budget, synchronization spans the whole SM array, and every replay ends with a workspace-clean pass and a cross-rank barrier. We present GC-MoE, an open-source FP8/FP4 MoE inference operator for NVIDIA Hopper and Blackwell GPUs that uses CUDA Green Contexts to split the device into a small communication partition and a large compute partition. Each role gets its own kernel, resource budget, and synchronization domain, so dispatch and GEMM tune independently. A three-node CUDA Graph (four on Hopper with fused shared experts) launches the dispatch and grouped-GEMM kernels as concurrent roots; a token-ring handshake starts computation on the first filled ring blocks, and double-buffered receive counters remove the trailing cross-rank barrier between replays. The compute partition runs operand-swapped tcgen05 block-scaled MMA on Blackwell and register-A WGMMA with in-register FP4 decoding on Hopper, with fused SwiGLU, requantization, and optional shared experts. On 8 H20 GPUs GC-MoE accelerates DeepSeek-V4.1-Flash decode by 1.188x on average on both the routed and shared-expert suites (peaks 1.296x and 1.353x); on 8 B300 GPUs it accelerates GLM-5.2 and DeepSeek-V4.1-Flash by 1.106x (1.123x with fused shared experts, peak 1.209x), beating Mega MoE at all 54 measured points at matched accuracy. GC-MoE reserves only 20 of 148 SMs on B300 for dispatch.
IBM Granite 3.0 models
Ollama partners with IBM to bring Granite 3.0 models to Ollama.
Llama 3.2 goes small and multimodal
Ollama partners with Meta to bring Llama 3.2 to Ollama.
Llama 3 is not very censored
Compared to Llama 2, Llama 3 feels much less censored. Meta has substantially lowered false refusal rates. Llama 3 will refuse less than 1/3 of the prompts previously refused by Llama 2.
Every update links back to its source.