←engineering
← All topics

engineering

English text is being prepared.

Public reading groups
36
Last 30 days
14
Directory status
Legacy topic

LatestGoogle A2UI Team and CopilotKit Explain How to Build Generative UI Applications

Latest reading groups

Duplicate reports of the same fact are grouped

  1. Google Developers BlogFirst-partyAnalysis
    AI score70

    Google A2UI Team and CopilotKit Explain How to Build Generative UI Applications

    The Google A2UI team and CopilotKit CEO Atai Barkai explain how to build generative UI applications using the A2UI open standard and CopilotKit. A2UI describes interfaces with declarative JSON, and the client only renders components from a trusted component catalog; the same response can be rendered to React, Angular, SwiftUI, Jetpack Compose, and Flutter. The article provides a code example for integrating CopilotKit with Google ADK, and explains the bidirectional flow, implemented via the AG-UI protocol, in which user actions are sent back and the agent regenerates the interface.

    Why read thisThe original article provides complete integration steps and bidirectional interaction examples for A2UI and CopilotKit, which can be used to evaluate how generative UI can be implemented in practice.

  1. PyTorch BlogFirst-partyProduct release
    AI score60

    PyTorch integrates FlyDSL backend on AMD GPUs

    The official PyTorch blog introduces that users of AMD MI350 series GPUs can now use FlyDSL through existing operator APIs, covering dense and grouped GEMM, MXFP8/MXFP4 scaled GEMM, RMSNorm, TopK, and attention kernels provided via the AOTriton 0.14b series, without calling custom kernels. On MI355X, BF16 dense GEMM achieves a 1.10x geometric mean speedup over the faster baseline among ATen and Triton, MXFP8 and MXFP4 achieve 1.58x and 1.68x over ATen respectively, and grouped GEMM achieves 1.20x over Triton. In vLLM end-to-end A/B tests, whole-request speedups are BF16 1.13x, MXFP8 2.04x, and MXFP4 3.01x, depending on the model and concurrency.

    Why read thisThe original text provides measured speedup multiples for each operator and vLLM end-to-end, along with how to enable them, which can be used to judge the benefit boundaries of low-precision inference on AMD GPUs.

  1. PyTorch BlogFirst-partyProduct release
    AI score87

    Google and Meta jointly launch TorchTPU, enabling PyTorch to run natively on TPUs

    Google and Meta's PyTorch teams have collaborated to launch the open-source project TorchTPU, providing a native PyTorch backend for Google TPUs; migration only requires changing model.to("cuda") to model.to("tpu"). The project supports both eager and torch.compile modes, adds a new DeferAndFuse eager mode, covers about 450 Aten operators, and has been verified to run out of the box on 4,917 Hugging Face models, with a Tier 1 pass rate of 98% and Tier 2 numerical consistency relative to GPUs of 97%. According to the official announcement, it has already been used in the inference and training production workloads of some major Google Cloud customers, and is integrated with vLLM, SGLang, TorchTitan, Ray, and TorchRec.

    Why read thisThe original article presents TorchTPU's design principles, architectural details, and multiple sets of measured data, which can be used to assess the actual cost of migrating PyTorch workloads to TPUs.

  1. inclusionai_new_reposFirst-partyModel releases
    AI score69

    English translation is being prepared.

    Ming-3.0-tts Logo

  1. Ant Ling: Developer BlogFirst-partyModel releases
    AI score69

    Ant Ling open-sources two 6B models in the Ming-Image-0.1-Design series

    Ant Ling has open-sourced the Ming-Image-0.1-Design series, comprising two 6B models: Design generates complete visual designs such as UIs, infographics, and posters from text requirements, while Layer decomposes a design image into 2–9 semantically independent RGBA layers; Design Skill and PPT Skill are also open-sourced. In the UI/UX Design evaluation updated by Artificial Analysis on September 18, 2026, Design ranks 1st among open-source models with an Elo score of 1082; Layer achieves the best results on all 12 metrics of Crello-Test, reducing single-inference time from 795 seconds to 183 seconds. After Ant's internal Huamei integrated Layer, the time to first obtain editable layers dropped from over 5 minutes to about 40 seconds.

    English text is being prepared.

    Why read thisThe two 6B models link design generation and layer decomposition into an editable pipeline, with leaderboard rankings and business deployment data.