We’re excited to welcome Mooncake to the PyTorch Ecosystem! Mooncake is designed to solve the “memory wall” in LLM serving. By integrating Mooncake’s high performance KVCache transfer and storage capabilities with PyTorch native inference engines like SGLang, vLLM, and TensorRT-LLM, it unlocks new levels of throughput and scalability for large language model deployments. Mooncake enables prefill decode disaggregation, global KVCache reuse, elastic expert parallelism, and serves as a fault tolerant PyTorch distributed backend. 🔗 #PyTorch# #OpenSourceAI# #LLM# #AIInfrastructure#

Introducing - the Agentic OS you've been waiting for. 🧩 Compose teams of specialised AI agents from plugins. No model lock-in. No vendor platform. Your infrastructure, your data. ✅ Privacy-first: sensitive data never leaves your infra in plaintext. Tokenised before every LLM call, with a verifiable receipt per round. ✅ Plugin-driven: channels, integrations, tools, sub-agents as signed ZIPs. ✅ Self-hostable: Docker Compose up and running in minutes. ✅ Built for EU operations: GDPR-aware by design, EN/DE bilingual. Public preview is live. 🌐 🔗 #OpenSource# #AI# #AIAgents# #Privacy# #SelfHosted#

The Linux Foundation Announces $12.5 Million in Grant Funding (via @AlphaOmegaOSS and @OpenSSF) @AnthropicAI , @AmazonWebServices, @GitHub, @Google, @GoogleDeepMind, @Microsoft, @OpenAI to Invest in Sustainable Security Solutions for #OpenSource#