Docker is embracing the ggml/llama.cpp on-device future Who is going to be next?

Excited to introduce BitNet b1.58 2B4T — the first large-scale, native 1-bit LLM🚀🚀 BitNet achieves performance on par with leading full-precision LLMs — and it’s blazingly fast⚡️⚡️uses much lower memory🎉 Everything is open-sourced — run it on GPU or your Macbook 🖥️⚙️

Released Minis v1.2.0 — a MIDI extension for Unity's Input System. Now supports iOS, Android, and Web. Use MIDI controllers just like gamepads. github.com/keijiro/Minis Web demo available (Chrome recommended): keijiro.tokyo/WebGPU-Test/Vf…

At #GlobalAzureTorino On stage Nino Crudele "Mastering AI Multi-Agent Cyber Warfare: Dall’Attacco alla Difesa Adattiva" GlobalAzure #GlobalAzure #CyberSecurity #AIAgent #MVPBuzz

📢Tightly Coupled Range Inertial Odometry and Mapping with Exact Point Cloud Downsampling This paper introduces a SLAM framework that achieves real-time CPU-only performance in dense, registration-error-minimization-based odometry and mapping, by leveraging exact point cloud

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent

I never saw an official video, so here is my little bit from the induction of Quake into the Strong Museum’s World Video Game Hall of Fame last month.

For my ComfyUI friends. Just created some open source nodes for prompt enhancing using a local LLM (all within #ComfyUI), auto prompt generating by picking random lines from text files. (hopefully in the official node manager soon as well) github.com/Brekel/ComfyUI…

Llama.cpp supports the new gpt-oss model in native MXFP4 format The ggml inference engine (powering llama.cpp) can run the new gpt-oss model with all major backends, including CUDA, Vulkan, Metal and CPU at exceptional performance. This virtually brings the unprecedented quality

🚀 Qwen3-30B-A3B-2507 and Qwen3-235B-A22B-2507 now support ultra-long context—up to 1 million tokens! 🔧 Powered by: • Dual Chunk Attention (DCA) – A length extrapolation method that splits long sequences into manageable chunks while preserving global coherence. •

Speed Is the Innovation - GPT-OSS:20B + llama.cpp + @neovim

Qwen-Code weekly release (v0.0.8) : ✨ Deep VS Code Integration: Get context-aware suggestions & inline diffs directly in your editor! Initialize with /ide and supercharge your workflow. 🔌 Enhanced MCP Support: Add, remove, list MCP servers via CLI (qwen mcp add|remove|list),

🔥 DeepCode has been trending on GitHub for 2 consecutive days! 🚀 Almost hitting 2k GitHub Stars! 🌟 Fully Open Source: github.com/HKUDS/DeepCode ✨ All-in-One Agentic Coding Framework ✨ • 📄 Paper2Code - Research to Implementation • 🌐 Text2Web - Natural Language to Frontend

Have you tried Storybook in the Google Gemini App yet? Whether it's bringing funny group chats to life or creating a special, personalized send-off for a team member, there's so much more than bedtime stories. The possibilities are endless! Available today for Google AI subscribers in

OpenAI gpt-oss with ultra long context is here!🚀 Introducing Unsloth Flex Attention which enables 61K context for gpt-oss bf16 training on a 80GB GPU. Unsloth achieves 8×longer context, 50% less VRAM & 1.5×faster training vs. all implementations. 🔗docs.unsloth.ai/basics/long-co…

3D Gaussian Splatting Driving Simulator! You know those YouTube walking tours? I think this could become a similar trend like driving around in a splat or taking your driver's license test in a 3DGS simulator.

Today Meta announced #Monarch, a new framework for distributed programming that delivers scalability without sacrificing performance. Monarch can be used to drive, or even debug, a large cluster in a notebook. It can also orchestrate large, fault tolerant model pre-training or

🚀 Excited to announce the release of ExecuTorch 1.0! Now, you can deploy PyTorch models seamlessly to edge devices—mobile, embedded, or desktop—without conversion or rewriting. ExecuTorch supports a wide range of hardware backends and model types, making on-device AI more

CUDA 13.1 is here. It is the biggest expansion of CUDA since it launched in 2006. We are introducing CUDA Tile, a new way to program GPUs that makes powerful AI and accelerated computing easier for more developers to use.

I'm working on plugging Qwen3-VL and SAM3 into Basketball AI; looks promissing - Qwen3-VL - identifies what teams are playing - SAM3 - tracks players using text prompts