惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

大猫的无限游戏
大猫的无限游戏
J
Java Code Geeks
小众软件
小众软件
D
Docker
腾讯CDC
H
Hackread – Cybersecurity News, Data Breaches, AI and More
V
V2EX
博客园 - 叶小钗
GbyAI
GbyAI
Microsoft Azure Blog
Microsoft Azure Blog
Stack Overflow Blog
Stack Overflow Blog
B
Blog RSS Feed
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 【当耐特】
IT之家
IT之家
博客园 - 司徒正美
M
MIT News - Artificial intelligence
T
The Blog of Author Tim Ferriss
The GitHub Blog
The GitHub Blog
罗磊的独立博客
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
L
LangChain Blog
阮一峰的网络日志
阮一峰的网络日志
C
Check Point Blog

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - AronDaron/dataset-generator: No-code desktop app for generating high-quality synthetic datasets to fine-tune LLMs — plan-then-execute pipeline, LLM-as-judge, HuggingFace upload. GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
Flex routing (EU and EFTA)
raffael_de · 2026-04-22 · via Hacker News - Newest: "LLM"

Flex routing lets customers in the European Union (EU) and the European Free Trade Association (EFTA) allow large language model (LLM) inferencing to occur outside the EU Data Boundary during periods of peak demand to help maintain a consistent Copilot experience. Inferencing is the processing step when an AI model executes the prompt to produce an output or response, such as summarizing content or answering a question.

No matter where LLM inferencing occurs, data will be encrypted in transit and at rest. Data at rest will continue to be stored inside the EU Data Boundary, except for limited pseudonymized data which may be stored outside the EU Data Boundary for security and operational purposes. For more information, see Ongoing partial data transfers.

Tenant administrators can change the flex routing setting at any time in the Microsoft 365 admin center or Power Platform admin center. The Microsoft 365 admin center setting applies to Microsoft 365 Copilot and Copilot Chat. The Power Platform admin center setting applies to Copilot experiences in Dynamics 365, Power Platform, and Copilot Studio.

Eligibility

Flex routing is available for customers with a sign-up location in a country or region in the EU or EFTA. For more information, see EU Data Boundary countries and datacenter locations.

Note that this setting will not be available for customers who have purchased multi-geo capabilities even if their tenant is listed as being in a country or region in the EU or EFTA. Customers can check their tenant’s country or region in the Microsoft 365 admin center.

Set up flex routing

Flex routing is on by default for eligible tenants that were created after March 25, 2026. For eligible tenants that existed before March 25, 2026, please check the Message Center for more details on your tenant’s default flex routing setting.

All tenant administrators are encouraged to check their tenant's flex routing setting to ensure it aligns with their company's requirements.

Enable flex routing

  1. Sign in to the Microsoft 365 admin center as an administrator assigned the AI Administrator role.
  2. Go to Copilot -> Settings -> View all -> Flex routing during peak load periods.
  3. Select Allow flex routing during periods of peak load.
    1. This setting allows LLM inferencing and the storage of associated pseudonymized data to occur outside the EU data boundary during periods of peak demand. Typically, these periods are limited in duration and do not run continuously.
  4. If you don’t want to allow flex routing, select Do not allow flex routing.
    1. If you select this option, LLM inferencing will occur inside the EU Data Boundary, even during periods of peak demand. All Microsoft 365 data processing and data residency commitments will continue to apply.

Frequently asked questions

Why can't I see the flex routing setting in the Microsoft 365 admin center?

The flex routing setting is only visible in the Microsoft 365 admin center for customers with a sign-up location in a country or region in the EU or EFTA. For more information, see EU Data Boundary countries and datacenter locations. This setting is also not available for customers who have purchased multi-geo capabilities even if their tenant is listed as being in a country or region in the EU or EFTA. Customers can check their tenant’s country or region in the Microsoft 365 admin center.

How does flex routing affect Microsoft’s EU data boundary commitments?

When flex routing is enabled, LLM inferencing may occur outside the EU Data Boundary during times of peak demand. Data remains encrypted in transit and at rest. Data will also continue to be stored at rest inside the EU Data Boundary except for limited pseudonymized data which may be stored outside the EU Data Boundary for security and operational purposes. For more information, see Ongoing partial data transfers. EU and EFTA customers can disable flex routing in the Microsoft 365 admin center at any time.

Where does LLM inferencing occur when flex routing is enabled?

If flex routing is enabled, LLM inferencing may occur in the United States, Canada, or Australia during times of peak demand.

Why can't I change the flex routing setting in the Power Platform admin center?

If flex routing is not allowed in the Microsoft 365 admin center, flex routing will be off by default in the Power Platform admin center and you will not be able to change the setting. If flex routing is allowed in the Microsoft 365 admin center, then the flex routing setting in the Power Platform admin center will be configurable.