Train and ship ML models without managing Kubernetes infrastructure. ☸️
Meet GKE Workspaces, an AI/ML notebook platform built on open source Kubeflow Workspaces with stateful GPU pause/resume and Cloud TPU scaling.
👇 Link in first reply
Why did Google donate Agent Substrate and gVisor to the @CloudNativeFdn? ☁️
AI agents spend 90%–95% of their time idle waiting for models, yet need sub-second wakeups.
Learn how Substrate runs on GKE:
👇 Link in first reply
Train in Python, serve in C++. ⚡
Meet XLA Serving Engine (XSE), our open source C++ runtime for serving JAX and StableHLO models across TPUs, GPUs, and CPUs with 2–5x the throughput of a Python server.
👇 Link in first reply
Building interactive 3D, AR, and WebXR apps usually means wrestling with heavy 3D asset pipelines.
Three-Live introduces an Apache 2.0 library + on-device Rust/Boa compiler turning procedural @threejs_org scripts into GLB, USDZ & WebXR in ms.
👇 Link in first reply
This Week in Open Source #21 is here! 🎃🌐
👻 Supply-chain ghosts (GhostAction & LiteLLM) & EU CRA fork costs
🤖 200+ OSS AI policies, Bootstrap agent triage & Genkit Go 1.14 HITL
⚡ TorchTPU, CNCF llm-d 1.0 & FOSDEM 2027
👇 Link in first reply