Join us

ContentUpdates and recent posts about ForgeMT..
Link
@varbear shared a link, 1 month ago
FAUN.dev()

Practical coding with AI Assistance

Developers using AI agents like Cursor are hitting a wall: vague, messy blob-code. Especially in frameworks likeLangChain, where sketchy training data can produce long-winded or broken output. The problem? AI generates "just vibes" instead of structure. The fix: go in with a plan. Aspec-driven, cont.. read more  

Practical coding with AI Assistance
Link
@kaptain shared a link, 1 month ago
FAUN.dev()

AWS Backup now supports Amazon EKS

AWS Backup just added support forAmazon EKS. Now you can back up cluster state and persistent volumes, no agents, no third-party hacks. It handles scheduling, retention, and immutability out of the box. Restore full clusters or drill down to specific components, even across Regions and accounts... read more  

Link
@kaptain shared a link, 1 month ago
FAUN.dev()

ConfigHub: Why Your Internal Developer Platform Needs It

See why GitOps often feels like a sprawl of configs, discover how to manage Configuration as Data for your Kubernetes platform, and learn how ConfigHub can help... read more  

Link
@kaptain shared a link, 1 month ago
FAUN.dev()

Using Komodo to Run Docker Commands from a Web Interface

Komodo drops a slick browser-based UI for wrangling Docker - containers, images, networks, and Compose stacks - through a real-time visual dashboard. Think native Docker meets one-click redeploys, host curation via agents, and reusable container configs that don’t make you hate YAML... read more  

Using Komodo to Run Docker Commands from a Web Interface
Link
@kaptain shared a link, 1 month ago
FAUN.dev()

KServe becomes a CNCF incubating project

KServe is upgrading.The CNCF pulled it into incubation, backing it astheKubernetes-native way to serve both generative and predictive AI. Translation: it’s not a side project anymore - it’s core infra. Version 0.15 steps up with tighter integrations across the stack:vLLM,Envoy Gateway,llm-d,Knative,.. read more  

KServe becomes a CNCF incubating project
Link
@kaptain shared a link, 1 month ago
FAUN.dev()

Amazon Elastic Kubernetes Service gets independent affirmation of its zero operator access design

Amazon EKS just went full Fort Knox. It now runs on azero operator accessmodel - meaning even AWS can’t peek inside your Kubernetes control or data plane. The setup leans on theNitro System’s confidential compute,guarded APIs, andmulti-party approval pipelines. NCC Group also kicked the tires and ga.. read more  

Link
@kaptain shared a link, 1 month ago
FAUN.dev()

Streamline Complex AI Inference on Kubernetes with NVIDIA Grove

NVIDIA releasedGrove, a Kubernetes API baked intoDynamo, to wrangle the chaos of modern AI inference. It pulls apart your big, messy model into clean, discrete chunks - prefill, decode, routing - and runs them like a single, orchestrated act. The trick?Custom hierarchical resources. They let Grove h.. read more  

Link
@kaptain shared a link, 1 month ago
FAUN.dev()

Prepare for the Kubernetes Administrator Certification and Pass

A tight 2-hour YouTube course built for theCKA examgrind. It's all real-world tasks: cluster setup, upgrades, troubleshooting. No fluff, just shell commands and Kubernetes in action. It walks through the gritty bits:etcdbackup and restore, node affinity, tolerations, and how to set upIngresslike som.. read more  

Prepare for the Kubernetes Administrator Certification and Pass
Link
@kala shared a link, 1 month ago
FAUN.dev()

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Researchers squeezed GPT-2-class performance out of a model trained on just1 billion tokens- 10× less data - by dialing in a sharp dataset mix:50% finePDFs, 30% DCLM-baseline, 20% FineWeb-Edu. Static mixing beat curriculum strategies. No catastrophic forgetting. No overfitting. And it hit90%+of GPT-.. read more  

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
Link
@kala shared a link, 1 month ago
FAUN.dev()

Jensen Huang's Stark Warning: China's 1 Million AI Workers vs America's 20,000

Nvidia CEO Jensen Huang, in some leaked comments, didn’t mince words: U.S. export bans aren’t hobbling China’s AI game - they’re fueling it. He pointed to Huawei’s 910C chip edging close to H100 territory, a forecast putting China ahead in AI compute by 2027, and a fast-growing local chip industry n.. read more  

Jensen Huang's Stark Warning: China's 1 Million AI Workers vs America's 20,000
ForgeMT is an open-source, production-grade platform designed to solve the complexity of running GitHub Actions runners at scale. Instead of teams managing their own fragile and duplicated CI runner setups, ForgeMT centralizes orchestration into a single, multi-tenant system built for scalability, security, and cost efficiency.

The platform provisions ephemeral runners on both EC2 and Kubernetes (EKS) using Terraform and Terragrunt, ensuring workloads scale up instantly and tear down to zero when idle, reducing costs. It enforces strong tenant isolation with AWS IAM, OIDC integration, and network segmentation, giving each team a secure boundary without requiring separate infrastructure.

ForgeMT integrates seamlessly with GitHub via a GitHub App and webhook events, automatically spinning up the right type of runner when jobs start. It supports advanced autoscaling strategies with Karpenter, spot instance optimization, and observability through centralized logging and monitoring.

By removing operational overhead, ForgeMT helps organizations accelerate delivery, cut cloud costs, and meet security requirements — all while giving developers fast, ephemeral CI runners that just work.