#cplusplus
FlashMLA is DeepSeek's optimized attention library that makes AI models run faster and use less memory. It works with advanced NVIDIA GPUs to speed up how language models process information, achieving up to 660 trillion floating-point operations per second. The library supports both dense and sparse attention modes, meaning it can focus on important tokens while skipping less relevant ones, reducing computational waste. For you, this means faster AI responses, lower costs for running large language models, and better performance on tasks like chatbots and code generation. The technology is open-source and integrates with popular AI frameworks like PyTorch and Hugging Face, making it accessible for developers building next-generation AI applications.
https://github.com/deepseek-ai/FlashMLA
⚖El TS fija doctrina sobre la capacidad y competencia de los plenos municipales para pronunciarse sobre cuestiones políticas de carácter internacional
#local#jurisprudencia
https://laadministracionaldia.inap.es/noticia.asp?id=1228267
🚀Jan-v1: локальная 4B-модель для веба — опенсорсная альтернатива Perplexity Pro
📌Что умеет
- SimpleQA: 91% точности, чуть выше Perplexity Pro — и всё это полностью локально.
- Сценарии: быстрый веб-поиск и глубокое исследование (Deep Research).
Из чего сделана
- Базируется на Qwen3-4B-Thinking (контекст до 256k), дообучена в Jan на рассуждение и работу с инструментами.
Где запускать
- Jan, llama.cpp или vLLM.
Как включить поиск в Jan
- Settings → Experimental Features → On
- Settings → MCP Servers → включите поисковый MCP (например, Serper)
Модели
- Jan-v1-4B: https://huggingface.co/janhq/Jan-v1-4B
- Jan-v1-4B-GGUF: https://huggingface.co/janhq/Jan-v1-4B-GGUF
@ai_machinelearning_big_data
#ai#ml#local#Qwen#Jan
#FitLocal#Find#Local#Trainers
Join the FitLocal: Find Local Trainers beta on ✈️#TestFlight
🔗 Link: https://testflight.apple.com/join/tJE8FBcS
Shared by Dimitri
#go#cli#database#database_management#dbms#environment#local#postgres#postgresql#supabase
Supabase CLI lets you run Supabase locally, manage database migrations, deploy functions, generate types from your schema, and make secure API calls. Install easily via npm (`npm i supabase --save-dev`), Homebrew, Scoop, or binaries for any OS, then run `supabase init` and `supabase start` to launch your full stack with local URLs and keys. This benefits you by speeding up development, testing changes offline without cloud costs, ensuring type safety, and simplifying CI/CD for reliable deploys.
https://github.com/supabase/cli