📢 Official Announcement: Qwen Partners with Fireworks AI to Accelerate Access to Qwen Family Models We are pleased to announce a strategic partnership between Qwen and Fireworks AI to deliver optimized, production-ready deployment of Qwen's closed weights models via the Fireworks Platform. @FireworksAI_HQ This collaboration empowers developers and enterprises to: ✅ Deploy Qwen models with lower latency and reduced fine tuning and inference costs ✅ Leverage enterprise-grade reliability, security, and scalability ✅ Integrate seamlessly into modern AI workflows 🔹 Get started with Qwen on Fireworks: #Qwen# #FireworksAI# #OpenSourceAI# #LLM# #AIInfrastructure# #ResponsibleAI# #DeveloperCommunity#

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#

🚀 Open-source upgrade unlocked. Tencent Hy-MT2 is now under Apache License 2.0 — maximum freedom for research, commercial use, fine-tuning, and derivatives. No strings attached.😎😎😎 Proud to push model weights back to the community. Our two variants are currently sitting at #1# and #4# on the Hugging Face trending leaderboard. Clone, fork, break things, ship feedback. The iteration loop is live.🔥 Let’s keep building the frontier together. #Tencent# #Hy# #HyMT2# #Apache2# #HuggingFace# #OpenSourceA#

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#

#OpenSource# doesn't scale by accident. Share how your organization approaches governance, contribution strategies, security, compliance, community engagement, & more at OSPOlogy + #OSPOSummit# China. 📅 September 7, Shanghai 🎤 Submit to speak by July 12:

More opensource goodness. We have just released a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code. Scan repositories, review changes, track findings over time, and run security checks in CI.