Yuri Bacciarini

Yuri Bacciarini

Italy

How to read logs from Kubernetes worker nodes using kubectl

How to read logs from Kubernetes worker nodes using kubectl

"I run k8s on a cloud provider so I don't care about worker nodes' logs and I'm so happy of that" Some days later.. Writing on google "How to access k8s worker node's logs in a SaaS solution ..."

Flipper Zero meets restaurants' pager systems (DDoS attack)

Flipper Zero meets restaurants' pager systems (DDoS attack)

How to use Flipper Zero to better understand what's behind restaurants' pager systems

Efficient way to troubleshoot on any systems

Efficient way to troubleshoot on any systems

There's no greater frustation of trying to troubleshoot on a system for many hours (or days) while the solution was under our nose for all the time.

How TorchServe could scale in a Kubernetes environment using KEDA

How TorchServe could scale in a Kubernetes environment using KEDA

I almost burned a 7K Euros GPU card (NVIDIA A100 PCIe GPU) to understand how a TorchServe could meet the increasing of ondemand inference requests at scale.

Serve AI models using TorchServe in Kubernetes at scale

Serve AI models using TorchServe in Kubernetes at scale

In a tipical MLOps pratice, among the various things, we need to serve our AI models to users exposing inference APIs. I tried a production ready framework (TorchServe) installing it on Azure Kubernetes Service and tested its power to the maximum.

Tweets by YBacciarini