Forsta runs Buoyant Enterprise for Linkerd across 40+ Azure Kubernetes clusters, roughly 2,000 pods per cluster, and about 400 services. Running it takes barely 0.1% of their operational headcount. Read the case study: https://t.co/hXMGIL2Evp
Couple of weeks ago I was a guest on #TheAIKubernetes Show where I had a good conversation with @wm about what it actually takes to run AI workloads on Kubernetes.
Most load balancers route on URL path. The OpenAI API spec puts the model ID in the request body. Standard load balancing doesn't work for model-based LLM routing. The Gateway API Inference Extension was built specifically for this.
We also got into agentic workloads and why they're different from inference, the identity and resource management challenges, and where Kubernetes is heading over the next year.
Watch our conversation: https://t.co/TPCG0WRPhi
#TheAIKubernetesShow #Kubernetes #AgenticAI #LLMInference
🤖 #AIAgents are powerful—but also unpredictable and risky when they start making autonomous API calls in your enterprise.
@BuoyantIO's CEO explains how @Linkerd's new #MCP support brings #zerotrust#security & real-time #observability to #agenticAI workloads.
https://t.co/UG0psgtLYn
See them at #KubeCon booth 440!
Big news for Linkerd and Windows users! Linkerd 2.19 just dropped, making us the *first* service mesh to officially support Windows nodes in Kubernetes. Get ready to extend Linkerd's power to your containerized Windows applications. Learn more 👉 https://t.co/Wj9TsSra3i