Latest Posts

42 posts
How many sandboxed pods can fit in a Pi?
The rationale of edge computing is simple: instead of moving data to centralized data centers, computation is brought closer to where data is produced. In practice, this means deploying software on hardware that lives in factory …
May 20, 2026
How many sandboxed pods can fit in a Pi?
Running gVisor on Raspberry Pi 5: A Kernel Configuration Adventure
If you’ve ever tried to run gVisor on a Raspberry Pi 5 and hit a cryptic failure, you’re not alone. The root cause turns out to be a single kernel configuration option, one that most people have never heard of. Let’s …
Mar 10, 2026
When ETCD Crashes, Check Your Disks First: A Pod CrashLoopBack Debugging Story
Setting up a cloud-edge continuum testbed for a computer vision demo taught us something fundamental about distributed systems: etcd doesn’t forgive slow storage.
Feb 19, 2026
AI Agents? Not on my host
Over the past few years, Large Language Models (LLMs) have changed how we interact with computers. Instead of navigating interfaces or reading documentation, we simply describe what we want in natural language.
Feb 11, 2026
A Lightweight C Library for Fetching OCI Artifacts
From Containers to KServe and vAccel Container images have become the standard unit of software packaging and deployment. They’re everywhere: in the cloud, on edge devices, and even in AI inference …
Oct 26, 2025
Keeping Our GitHub Runners Alive with Dependabot
When a Release Breaks Your CI We’re a small engineering team. Everyone’s busy! Some days we’re deep in container runtime dev, other days we’re debugging transport layers for vAccel or measuring latency …
Oct 23, 2025
When More Cores Means Less Speed: Debugging PyTorch with Valgrind on ARM
If you’ve ever tried to debug a PyTorch program on an ARM64 system using Valgrind, you might have stumbled on something really odd: “Why does it take so long?”. And if you’re like us, you would probably try to run it …
Jul 11, 2025
“It’s just localhost. How slow could it be?”
That’s what we thought when setting up a BERT-based hate speech classifier. This was part of a broader experiment using vAccel, our hardware acceleration abstraction for AI inference across the Cloud-Edge-IoT continuum.
Jun 22, 2025
Horror Story: The Fiasco of armv7l GHA Self-hosted Runners for Ubuntu 24.04
In the world of DevOps and CI/CD pipelines, GitHub Actions stands out as a powerful tool for automation. However, as with all tools, the devil lies in the details; or in this case, the dependency chain. This post dives into the recent …
Dec 3, 2024
Cloud-Native IoT: Redefining Device Management with k8s
The world of IoT is expanding rapidly, bringing with it a growing demand for scalable, secure, and efficient device management solutions. Traditional approaches often struggle with the complexities of managing heterogeneous fleets of …
Nov 23, 2024
Sandboxing WASM with Unikernels for Secure Cloud-Native Deployments
WebAssembly (WASM) is rapidly emerging as a transformative technology in the cloud-native ecosystem. Its binary instruction format, designed for execution on a stack-based Virtual Machine (VM), enables …
Nov 21, 2024
Fosscomm 2024
If you’re into open-source and tech meetups, FOSSCOMM is the event to be at. This year, it was held in Thessaloniki, organized by the open-source community of the University of Macedonia (UoM), and they absolutely crushed it with the …
Nov 11, 2024
Kubebuilder: Extending the k8s API to match applications' needs
Kubernetes is the de-facto platform to automate the management, deployment, and scaling of containerized applications. One of its strongest features is its ability to scale, allowing users to customize the system according to their …
Nov 7, 2024
Cloud-native IoT deployments with Akri
As the Internet of Things (IoT) continues to expand, managing a large number of heterogeneous devices with diverse requirements and characteristics has become essential. The Cloud computing ecosystem has provided a vast amount of tools …
Aug 8, 2024
Navigating ESP32 wireless connectivity issues
Have you ever found yourselves scratching your heads over perplexing connectivity issues? If you’re anything like us, you’ve probably encountered your fair share of head-scratching moments. In this short post, …
May 8, 2024
Build Multi-arch CI pipelines with Github Actions Self-hosted Runners
As per a well-known and established definition:
Feb 5, 2024
Updating our testing framework using Catch2
Testing is an important part of software development, yet is often neglected in many projects. We felt our code base for vAccel had reached a stage where the foundations for a proper testing framework would be a good decision.
Jan 10, 2024
vAccel-go: Golang bindings for vAccel
To facilitate the use of vAccel, we provide bindings for popular languages, apart from C. Essentially, the vAccel C API can be called from any language that interacts with C libraries. Building on this, we are thrilled to present …
Jan 2, 2024
Optimizing Performance with Unikernels: Exploring Container Runtimes for Serverless Workloads with Knative Benchmarking
In our previous posts, we walked through the process of configuring various low-level container runtimes in Knative using the RuntimeClass feature of K8s. We detailed the setup for isolation mechanisms like gVisor, with a special …
Nov 24, 2023
urunc: Introducing a unikernel container runtime
This post is about urunc, a tool that we build to treat unikernels as containers and properly introduce unikernels to the cloud-native world! Essentially, urunc is a container runtime able to spawn unikernels that reside …
Nov 14, 2023
Knative: A Deep Dive into K-Deployments across diverse Runtimes (part II)
The Serverless computing paradigm has revolutionized the way applications are deployed. In a serverless architecture, developers can focus solely on writing code without the need to provision or manage servers.
Oct 9, 2023
Knative: Serverless Computing in K8s (part I)
Serverless computing is a revolutionary approach to cloud computing that allows developers to focus solely on writing and deploying code without having to manage server infrastructure.In a traditional server-based model, developers …
Sep 27, 2023
Isolated, hardware-accelerated functions on Jetson AGX Orin
Following up on a successful VM boot on a Jetson AGX Orin, we continue exploring the capabilities of this edge device, focusing on the cloud-native aspect of application deployment.
Sep 24, 2023
Boot a VM on an NVIDIA Jetson AGX Orin
In 2022, NVIDIA released the Jetson Orin modules, specifically designed for extreme computation at the Edge. The NVIDIA Jetson AGX Orin modules deliver up to 275 TOPS of AI performance with power configurable between 15W and 60W.
Feb 13, 2023
Remote FPGA acceleration: vAccel on PYNQ-Z1
Running applications that need hardware acceleration in public clouds remains a challenge, both for end-users and for service providers. The reasons for this are mostly related to the complicated hardware abstractions that acceleration …
Jan 20, 2023
PYNQ-Z1 bringup
The PYNQ-Z1 board is the hardware platform for the PYNQ open-source framework. It features a Zynq-7000 (XC7Z020-1CLG400C) All Programmable System-On-Chip (APSoC), integrating a feature-rich dual-core Cortex-A9 based processing system …
Jan 5, 2023
Kata Containers: Build and configure Firecracker
Picking up from where we left in our previous post, we will now install AWS Firecracker and configure Kata Containers to use it as their hypervisor.
Mar 28, 2022
Kata Containers: Build and configure QEMU
Picking up from where we left in our previous post, we will now install QEMU and configure Kata Containers to use QEMU as their hypervisor.
Mar 28, 2022
Build Kata Containers from source on x86 and arm64
Kata Containers enable containers to be seamlessly executed in Virtual Machines. Kata Containers are as light and fast as containers and integrate with the container management layers, while also delivering the security advantages of …
Mar 24, 2022
Running containers on Firecracker microVMs using kata on kubernetes
This is the first of a number of posts regarding the orchestration, deployment and scaling of containerized applications in VM sandboxes using kubernetes, kata-containers and AWS Firecracker microVMs. We have gathered some notes during …
Jul 9, 2021
Hardware acceleration in the Age of Functions (vol II)
In our previous post we spoke about the potential solutions for deploying serverless offerings with hardware acceleration support. With the increasing adoption of the serverless and FaaS paradigms, providers will need to offer some …
Dec 4, 2020
Hardware acceleration in the Age of Functions
The debate on how to deploy applications, monoliths or micro services, is in full swing. Part of this discussion relates to how the new paradigm incorporates support for accessing accelerators, e.g. GPUs, FPGAs. That kind of support …
Jun 1, 2020
Fosdem 2020
Earlier this month we visited FOSDEM, an absolutely open and free event for developers, open-source vendors and enthusiasts to meet, share their ideas and news, and discuss the latest in open source. Talks at FOSDEM are usually …
Feb 26, 2020
Build a single-app rootfs for Firecracker MicroVMs
Spawning applications in the cloud has been made super easy using container frameworks such as docker. For instance running a simple command like the following
Oct 21, 2019
Porting Firecracker to a Raspberry Pi 4
Since we got our hands on the new Raspberry Pi 4, we started exploring how various virtualization technologies behave on the board. First thing we tried is how to run Nabla on it and how it compares to native KVM.
Oct 21, 2019
Build a 64bit bootable image for a Raspberry Pi 4
Given the traction our previous post got, we thought we should jot down the steps to build a 64-bit bootable image for a RPi4. The distro we’re most familiar with is Debian, so we’ll go with a debian-like distro like …
Jul 14, 2019
Playing with a Raspberry Pi 4 64-bit
Lightweight virtualization is a natural fit for low power devices and, so, seeing that the extremely popular Raspberry Pi line got an upgrade, we were very keen on trying the newly released Raspberry Pi 4 model B.
Jul 10, 2019
How to build a python snippet for running in a Nabla container
In our previous posts, we saw how to build the toolchain for a Nabla container, and also how we can use this toolchain to run applications as unikernels using Nabla.
Feb 23, 2019
Build a Nabla Docker Image
In this post, we go through the basic steps for containerizing a unikernel application and running it on nabla runnc. Checkout nabla containers and in particular runnc.
Feb 23, 2019
Building the Nabla containers toolchain for `aarch64`
[UPDATE: Revise instructions and links to use latest upstream nabla repo with merged aarch64 support.]
Jan 24, 2019
Run a rumprun unikernel on a `RPi3`
[UPDATE: Revise instructions to reflect upstream nabla changes.]
Jan 24, 2019
Experiences from porting nabla containers to an ARMv8 board
[UPDATE: Rumprun aarch64 support has now been merged in upstream nabla.]
Jan 23, 2019