ContentPosts from @diogoalexandria..
Link
@faun shared a link, 7 months, 2 weeks ago

KubeCon Europe: How Kubernetes Handles 6G, LLMs and Deep Space

Kuberneteswrangles with the chaos of infrastructure stretching across continents, but the community's already crafting clever fixes... read more  

Link
@faun shared a link, 7 months, 2 weeks ago

Cold-Starting LLMs on Kubernetes in Under 30 Seconds

RedesigningLLM cold start strategy sliced launch times from 10 minutes tounder 30 secondsby exploitingFUSEandobject storagefor on-demand GPU loading—a revelation for Kubernetes scaling... read more  

Cold-Starting LLMs on Kubernetes in Under 30 Seconds
Link
@faun shared a link, 7 months, 2 weeks ago

The Next Evolution of DigitalOcean Kubernetes: Introducing Features that Unlock Superior Scalability for Growing Businesses

DigitalOceanjust cranked up the cluster game to a cool1,000nodes, injectedeBPF-based routingfor a performance boost, and rolled outManaged Ciliumto keep things rock steady. Scale orchestration? Now it's on rocket fuel... read more  

The Next Evolution of DigitalOcean Kubernetes: Introducing Features that Unlock Superior Scalability for Growing Businesses
Link
@faun shared a link, 7 months, 2 weeks ago

Introducing kube-scheduler-simulator

kube-scheduler-simulatorlets you peek into the mind of Kubernetes’ scheduler. You can poke and prod at scheduling decisions without risking a real cluster meltdown. Add custom plugins like a pro, no sweat. Forget blindsiding surprises. The simulator mirrors production with eerie accuracy—sync resour.. read more  

Introducing kube-scheduler-simulator
Link
@faun shared a link, 7 months, 2 weeks ago

CKA Prep: CKA Exam Overview and Preparation Strategy

CKA exam:Juggle up to 6 Kubernetes clusters like a pro. Command rolling updates, Ingress, and persistent storage with flair. Imperative commands? Your secret weapon to snatch victory... read more  

Link
@faun shared a link, 7 months, 2 weeks ago

Google Cloud unveils AI-focused updates to Kubernetes Engine

Meet theCluster Director for GKE. This beast masters GPU/TPU clusters seamlessly, herding them with Kubernetes APIs like a rodeo star. Meanwhile, theGKE Inference Gatewayramps up AI model performance. It's like magic but real: Serving costs tumble by up to30%. Tail latency? Chopped by up to60%... read more  

Link
@faun shared a link, 7 months, 2 weeks ago

Optimize Gemma 3 Inference: vLLM on GKE 🏎️💨

GKE Autopilot's GPUmeans business—AI inference tasks don’t stand a chance. Just two arguments and, bam, you’ve unleashed NVIDIA's beastly Gemma 3 27B model, which chugs a massive46.4GB VRAM. ⚡️ Meanwhile, vLLM squeezes the models with bf16 precision, though optimization requires wrestling with algor.. read more  

Optimize Gemma 3 Inference: vLLM on GKE 🏎️💨
Link
@faun shared a link, 7 months, 2 weeks ago

Kubernetes 1.33 – What you need to know

Kubernetes 1.33 shakes things up with game-changing updates.LIST streaming encodingtrims down API Server memory like a chef with a sharp knife. Deliberate deletion orders lock down security tighter than a drum. And get this:in-place updatesfor Pod resources ditch those annoying restarts! Finally, us.. read more  

Kubernetes 1.33 – What you need to know
Link
@anjali shared a link, 7 months, 2 weeks ago
Customer Marketing Manager, Last9

Observability vs APM: What’s the Real Difference?

Observability goes beyond APM—it's not just about metrics, it's about understanding why things break, not just that they did.

o11Y VS APM
Link
@anjali shared a link, 7 months, 2 weeks ago
Customer Marketing Manager, Last9

Logging vs Monitoring: What’s the Real Difference?

Logging and monitoring work together, but they’re not the same. Here’s how they help you understand, fix, and improve your systems.

logging