我的收藏提交工具
FOXAI SEARCH

全站搜索

新闻报道 226

inference-systems

b12179

The update introduces support for 3D convolution (conv_3d) on Hexagon hardware by generalizing the existing conv_2d implementation. It leverages the HMX tiled path, folds kernel dimensions into a virtual row, and uses a shared solver with an is3d flag. The host computes unfold divisors to avoid device-side division, prevents DMA queue overflow, and improves tile size selection based on VTCM usage. Additional changes include handling arbitrary positive strides, preserving load/shuffle paths for small strides, and fixing compiler warnings.

翻译服务暂未运行，当前显示原文。
llama.cpp releases
inference-systems

b12180

The release adds the Kimi-K3.1-Pro text model to llama.cpp, replacing full-attention MLA layers in K3 with DSA (Dynamic Sparse Attention) layers featuring a lightning indexer. The indexer uses an additive mask over the cache and reuses sparse flash attention paths, while preserving existing KDA layers and MoE components. The model's architecture includes four indexer tensors per DSA layer, hybrid memory for caching, and maintains quantization integrity by excluding indexer parameters from quant overrides. Verified against HF checkpoint with identical PPL beyond context length, and supports multiple platforms including macOS, Linux, Windows, Android, and iOS.

翻译服务暂未运行，当前显示原文。
llama.cpp releases
coding-engineering

DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway

DeepSeek V4.1 Flash 1017 Ultrafast, offering over 1,000 tokens per second, is now available via Fireworks' accelerated serverless endpoint on Vercel's AI Gateway. The model features a 1M-token context window and is optimized for interactive coding, reasoning, and agentic workflows. It is in public preview with no waitroom or session time limits. Developers can use it by specifying the model name in their code or through tools like Claude Code, Codex, and Cursor after setting up the latest Vercel CLI. AI Gateway provides unified API access, usage tracking, cost management, and performance optimizations without markup or platform fees.

翻译服务暂未运行，当前显示原文。
Vercel
enterprise-apps

SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints

Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator. This post shows how two optional API fields place one model per partition, and what we measured against a whole older GPU.

翻译服务暂未运行，当前显示原文。
AWS Machine Learning Blog
startup-projects

Show HN: Combining Bursts of Images

An approach of taking many photos to enhance one final image is a technique called "stacking". Stacking alone doesn't account for everything so this is a take that helps get better alignment of images, allows comparisons, and drop bad images that dont match. Its not super resolution but it feels like when you look at it. it reduces the noise and makes it look more organic shot with less expensive hardware. enjoy! Comments URL: https://news.ycombinator.com/item?id=50401218 Points: 1 # Comments: 0

翻译服务暂未运行，当前显示原文。
Hacker News Show HN