Introduction Hey, welcome back to my ultimate Kubernetes tutorials! So far, we've explored ClusterIP and NodePort, but what if you need to route traffic outside your cluster or expose your app with a real external IP? That’s where ExternalName and LoadBalancer services come in. ExternalName lets your pods seamlessly connect to external services using DNS, while LoadBalancer provides a publicly accessible endpoint for your app. In this post, we’ll break down how they work, when to use them, and how to configure them in your Kubernetes cluster. Let’s dive in! 🚀 Exploring ExternalName Service Okay, we're still in my nginx/testpod environment in namespace service-type-test In our last post, we have ClusterIP running, let's delete it to get a clean environment to start: kubectl apply -f /home/admin/nginx-deployment/nginx-clusterip-service.yaml kubectl get service -n service-type-test -o wide You should not see any service is running in above output. Now, let's work on  ExternalName! Creating an ExternalName service is simpler than creating NodePort or ClusterIP , a little bit... create a file /home/admin/nginx-deployment/nginx-externalname-service.yaml: apiVersion: v1 kind: Service metadata: name: nginx-service namespace: service-type-test spec: type: ExternalName externalName: my-nginx.external.local Unlike ClusterIP, NodePort, LoadBalancer, or Headless services, this service does not select backend pods. Instead, it just creates a DNS alias that redirects traffic to an external hostname. So: No selector needed → It does not route traffic to Kubernetes pods. No labels needed → There’s no pod matching required since it’s just a DNS pointer. It simply returns the CNAME record when queried inside the cluster. Simpler on Kubernetes side, but more manual steps on your own side…

Introduction Hey, welcome back to my ultimate Kubernetes tutorials! Now that our 1 master + 4 worker node cluster is up and running, it’s time to dive into NodePort vs. ClusterIP—two key service types in Kubernetes. Services act as the traffic controllers of your cluster, making sure pods can communicate reliably. Without them, your pods would be like isolated islands, unable to connect in a structured way. Pods are ephemeral, constantly changing IPs. That’s where Kubernetes services step in—ensuring stable access, whether for internal pod-to-pod networking or external exposure. Let’s break down how they work and when to use each! 🚀 Before we start, here comes a quick summary for common Four Kubernetes services: Service Type Description Use Case ClusterIP Exposes the service internally within the cluster. No external access. Internal microservices that only communicate within Kubernetes. NodePort Exposes the service on a static port on each node's IP, making it accessible externally. Basic external access without a LoadBalancer. LoadBalancer Creates an external load balancer that directs traffic to the service. Production environments requiring automated load balancing. ExternalName Maps a Kubernetes Service to an external DNS name instead of forwarding traffic. Redirecting traffic to external services outside the cluster. Ps. Headless Service is also a Kubernetes Service type, but it behaves differently from the usual four. In this post, I will guide you to: ✅ Create an Nginx deployment running on a single node✅ Expose it using a NodePort Service✅ Verify accessibility inside and outside the cluster ✅ Expose it using a ClusterIP Service ✅ Verify accessibility inside and outside…

Introduction Welcome back to the Kubernetes tutorial series! Now that our base image and local server are ready, it’s time for the real action—Kubernetes cluster setup with Flannel. I'll spin up one Kubernetes master and 4 worker nodes, forming a local Kubernetes cluster that’s ready for real workloads. No more theory—let’s build something real! 🚀 Clone baseimage to k8s-1 as The Kubernetes VM Base Image Before jump on our Kubernetes cluster setup, let's start from my Mac's terminal, clone from Base Image - Rocky 9 as k8s-base: ❯ vmrun clone /Users/geekcoding101.com/Virtual\ Machines.localized/baseimage-rocky9.vmwarevm/baseimage-rocky9.vmx /Users/geekcoding101.com/Virtual\ Machines.localized/k8s-1.vmwarevm/k8s-1.vmx full ❯ sed -i '' 's/displayName = "Clone of baseimage-rocky9"/displayName = "k8s-1"/' "/Users/geekcoding101.com/Virtual Machines.localized/k8s-1.vmwarevm/k8s-1.vmx" Make sure you've stopped the baseimage VM, start the k8s-base VM. The steps here I've mentioned details in Part 2, in short, after above command, we need to rescan in VMFusion and SSH as root into the k8s-base using the IP172.16.211.3 of the base VM, preapre the input file /opt/share_tools/init_data/k8s-1_vm_input.json: { "hostname": "k8s-1", "ip": "172.16.8.11", "subnet": "24", "gateway": "172.16.211.2", "dns1": "172.16.211.100", "dns2": "8.8.8.8", "domain": "dev.geekcoding101local.com", "ansible_key_path": "~/.ssh/ansible_ed25519", "ssh_key_path": "~/.ssh/ssh_ed25519" } Then using VMFusion console to login into the VM, perform below command to generate SSH keys and setup networking: ansible-playbook /opt/share_tools/bin/configure_vm.yml -e "input_file_path=/opt/share_tools/init_data/k8s-1_vm_input.json" Now I can connect from SSH passwordlessly via the new IP 172.16.8.11. Test DNS Please note here is testing our local DNS server to ensure it's working in our Kubernetes cluster setup. But it's not going to replace CoreDNS... Anyway, ensure the DNS server localserver(172.16.211.100) we setup in Part 2 is running. Ensure the 172.16.211.100 is on top of  /etc/resolv.conf , should…

Introduction Hey there! Ready to take this Kubernetes setup to the next level? 🚀 In Part 1, we got our base VM image up and running—nice work! Now, in Part 2, I am going to clone that image to set up a local server as a DNS server and NTP server. I was considering to incorporate the steps to setup Kubernetes master and worker nodes, but seems too much. Anyway, a real cluster is coming soon! 😎 Excited? Let’s dive in and make some magic happen. 🔥 Create localserver VM Clone from Base Image Rocky 9 vmrun clone /Users/geekcoding101.com/Virtual\ Machines.localized/baseimage-rocky9.vmwarevm/baseimage-rocky9.vmx /Users/geekcoding101.com/Virtual\ Machines.localized/localserver.vmwarevm/localserver.vmx full sed -i '' 's/displayName = "Clone of baseimage-rocky9"/displayName = "localserver"/' "/Users/geekcoding101.com/Virtual Machines.localized/localserver.vmwarevm/localserver.vmx" cat "/Users/geekcoding101.com/Virtual Machines.localized/localserver.vmwarevm/localserver.vmx" | grep disp Above commands is to clone the base VM image (display name in VMFusion is Clone of baseimage-rocky9) as a new one, then update the display name of the new VM to localserver instead of Clone of baseimage-rocky9. Now, you probably need to run a scan in VMware Fusion to see the newly added VM: Customize the Local Server VM First, stop the baseimage VM and start the localserver VM to avoid network conflict. Now we can SSH as root into the localserver VM by using the IP172.16.211.3 of the base VM. Remember the script /opt/share_tools/bin/configure_vm.yml we created in Ultimate Kubernetes Tutorial - Setting Up a Thriving Multi-Node Cluster on Mac: Part 1. Let's preapre the input file /opt/share_tools/init_data/localserver_vm_input.json: { "hostname": "localserver", "ip": "172.16.211.100", "subnet": "24", "gateway": "172.16.211.2", "dns1": "8.8.8.8", "dns2": "8.8.4.4", "domain": "dev.geekcoding101local.com", "ansible_key_path": "~/.ssh/ansible_ed25519", "ssh_key_path": "~/.ssh/ssh_ed25519" } I…

Introduction Hey there! Welcome to this Kubernetes tutorial! Ever dreamed of running a real multi-node Kubernetes (K8s) cluster on your laptop instead of settling for Minikube’s diet version? A proper real multi-node Kubernetes environment requires virtual machines, and until last year, VMware Fusion was a paid product—an obstacle for many. I know there are alternatives, like KVM, Oracle VirtualBox, and even Minikube’s so-called multi-node mode ----but let’s be real: I’ve got a beast of a MacBook Pro, so why not flex its muscles and spin up a legit multi-node cluster? 🚀 But great news! On November 11, 2024, VMware announced that Fusion and Workstation are now free for all users! The moment I stumbled upon this announcement, I was thrilled. Time to roll up my sleeves, fire up some VMs, and make this cluster a reality. Kick off my Kubernetes tutorial! Let’s dive in! 🚀 Project Overview My Goal In this series of Kubernetes tutorial, I want to set up a full Kubernetes cluster on my MacBook Pro using VMware Fusion, creating multiple VMs to simulate real-world deployment and practice my DevOps and IaC (Infrastructure as Code) skills. Planned Setup Create a VM as Base VM (Rocky Linux 9) Configure networking Update system packages Disable firewalld Enable SSH passwordless login from local Mac to the base VM Set up zsh, tmux, vim and common aliases Install Miniforge for Python environment management Install and configure Ansible Set up a Local Server Node (localserver) Clone from the above base VM image Create an Ansible script to customize the base VM image withe new…

Transformers are changing the AI landscape, and it all began with the groundbreaking paper "Attention is All You Need." Today, I explore the Introduction and Background sections of the paper, uncovering the limitations of traditional RNNs, the power of self-attention, and the importance of parallelization in modern AI models. Dive in to learn how Transformers revolutionized sequence modeling and transduction tasks! 1. Introduction Sentence 1: Recurrent neural networks, long short-term memory [13] and gated recurrent [7] neural networks in particular, have been firmly established as state-of-the-art approaches in sequence modeling and transduction problems such as language modeling and machine translation [35, 2, 5]. Explanation (like for an elementary school student): There are special types of AI models called Recurrent Neural Networks (RNNs) that are like people who can remember things from the past while working on something new. Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) are improved versions of RNNs. These models are the best performers (state-of-the-art) for tasks where you need to process sequences, like predicting the next word in a sentence (language modeling) or translating text from one language to another (machine translation). Key terms explained: Recurrent Neural Networks (RNNs): Models designed to handle sequential data (like sentences, time series). Analogy: Imagine reading a book where each sentence depends on the one before it. An RNN processes the book one sentence at a time, remembering earlier ones. Further Reading: RNNs on Wikipedia Long Short-Term Memory (LSTM): A type of RNN that solves the problem of forgetting important past information. Analogy: LSTMs are like a memory-keeper that…

Below is a comprehensive table of key terms used in the paper "Attention is All You Need," along with their English and Chinese translations. Where applicable, links to external resources are provided for further reading. English Term Chinese Translation Explanation Link Encoder 编码器 The component that processes input sequences. Decoder 解码器 The component that generates output sequences. Attention Mechanism 注意力机制 Measures relationships between sequence elements. Attention Mechanism Explained Self-Attention 自注意力 Focuses on dependencies within a single sequence. Masked Self-Attention 掩码自注意力 Prevents the decoder from seeing future tokens. Multi-Head Attention 多头注意力 Combines multiple attention layers for better modeling. Positional Encoding 位置编码 Adds positional information to embeddings. Residual Connection 残差连接 Shortcut connections to improve gradient flow. Layer Normalization 层归一化 Stabilizes training by normalizing inputs. Layer Normalization Details Feed-Forward Neural Network (FFNN) 前馈神经网络 Processes data independently of sequence order. Feed-Forward Networks in NLP Recurrent Neural Network (RNN) 循环神经网络 Processes sequences step-by-step, maintaining state. RNN Basics Convolutional Neural Network (CNN) 卷积神经网络 Uses convolutions to extract features from input data. CNN Overview Parallelization 并行化 Performing multiple computations simultaneously. BLEU (Bilingual Evaluation Understudy) 双语评估替代 A metric for evaluating the accuracy of translations. Understanding BLEU This table provides a solid foundation for understanding the technical terms used in the "Attention is All You Need" paper. If you have questions or want to dive deeper into any term, the linked resources are a great place to start!

Today marks the beginning of my adventure into one of the most groundbreaking papers in AI for transformer: "Attention is All You Need" by Vaswani et al. If you’ve ever been curious about how modern language models like GPT or BERT work, this is where it all started. It’s like diving into the DNA of transformers — the core architecture behind many AI marvels today. What I’ve learned so far has completely blown my mind, so let’s break it down step by step. I’ll keep it fun, insightful, and bite-sized so you can learn alongside me! From today, I plan to study one or two pages of this paper daily and share my learning highlights right here. Day 1: The Abstract The abstract of "Attention is All You Need" sets the stage for the paper’s groundbreaking contributions. Here’s what I’ve uncovered today about the Transformer architecture: The Problem with Traditional Models: Most traditional sequence models rely on Recurrent Neural Networks (RNNs) or Convolutional Neural Networks (CNNs). These models have limitations: RNNs are slow due to sequential processing and lack parallelization. CNNs struggle to capture long-range dependencies effectively. Transformer’s Proposal: The paper introduces the Transformer, a new architecture that uses only Attention Mechanisms while completely removing recurrence and convolution. This approach makes transformers faster and more efficient. Experimental Results: On WMT 2014 English-German translation, the Transformer achieves a BLEU score of 28.4, surpassing previous models by over 2 BLEU points. WMT (Workshop on Machine Translation) is a benchmark competition for translation models, and this task involves translating English text into German.…

On December 20, 2024, OpenAI concluded its 12-day "OpenAI Christmas Gifts" campaign by revealing two groundbreaking models: o3 and o3 mini. At the same time, the ARC Prize organization announced OpenAI's remarkable performance on the ARC-AGI benchmark. The o3 system scored a breakthrough 75.7% on the Semi-Private Evaluation Set, with a staggering 87.5% in high-compute mode (using 172x compute resources). This achievement marks an unprecedented leap in AI's ability to adapt to novel tasks, setting a new milestone in generative AI development. The o3 Series: From Innovation to Breakthrough OpenAI CEO Sam Altman had hinted that this release would feature “big updates” and some “stocking stuffers.” The o3 series clearly falls into the former category. Both o3 and o3 mini represent a pioneering step towards 2025, showcasing exceptional reasoning capabilities and redefining the possibilities of AI systems. ARC-AGI Performance: A Milestone Achievement for o3 The o3 system demonstrated its capabilities on the ARC-AGI benchmark, achieving 75.7% in efficient mode and 87.5% in high-compute mode. These scores represent a major leap in AI's ability to generalize and adapt to novel tasks, far surpassing previous generative AI models. What is ARC-AGI? ARC-AGI (AI Readiness Challenge for Artificial General Intelligence) is a benchmark specifically designed to test AI's adaptability and generalization. Its tasks are uniquely crafted: Simple for humans: Tasks like logical reasoning and problem-solving. Challenging for AI: Especially when models haven’t been explicitly trained on similar data. o3’s performance highlights a significant improvement in tackling new tasks, with its high-compute configuration setting a new standard at 87.5%. How o3 Outshines Traditional LLMs:…

Ray Serve is a cutting-edge model serving library built on the Ray framework, designed to simplify and scale AI model deployment. Whether you’re chaining models in sequence, running them in parallel, or dynamically routing requests, Ray Serve excels at handling complex, distributed inference pipelines. Unlike Ollama or FastAPI, it combines ease of use with powerful scaling, multi-model management, and Pythonic APIs. In this post, we’ll explore how Ray Serve compares to other solutions and why it stands out for large-scale, multi-node AI serving. Before Introducing Ray Serve, We Need to Understand Ray What is Ray? Ray is an open-source distributed computing framework that provides the core tools and components for building and running distributed applications. Its goal is to enable developers to easily scale single-machine programs to distributed environments, supporting high-performance tasks such as distributed model training, large-scale data processing, and distributed inference. Core Modules of Ray Ray Core The foundation of Ray, providing distributed scheduling, task execution, and resource management. Allows Python functions to be seamlessly transformed into distributed tasks using the @ray.remote decorator. Ideal for distributed data processing and computation-intensive workloads. Ray Libraries Built on top of Ray Core, these are specialized tools designed for specific tasks. Examples include: Ray Tune: For hyperparameter search and experiment optimization. Ray Train: For distributed model training. Ray Serve: For distributed model serving. Ray Data: For large-scale data and stream processing. In simpler terms, Ray Core is the underlying engine, while the various tools (like Ray Serve) are specific modules built on top of it to handle specific functionalities. Now Let’s Talk…