Had an AWESOME conversation with the @allthingsopen.bsky.social community about local LLMs on small hardware: model compression can quantize a model from 220 GB → 55 GB with <1% accuracy loss, and inference engines like vLLM help run them fast and efficiently.
🎥 www.youtube.com/watch?v=xGqV...
🔌 Messy data meets LLMs!
Join Andy Igdal and Cedric Clyburn (@cedricclyburn.bsky.social) at DevBcn 2026.
Learn how Python and AI can tackle residential electrification data in the Big Data & AI track! 📊🤖
📅 June 16-17
🔗 buff.ly/dz1tICU
#devbcn26
Thanks! Happy to be back again this year :)
Check out the recording below!
🎥 RamaLama: Making working with AI Models Boring: www.youtube.com/watch?v=CYxw...
Self-hosting LLM’s typically includes a set of requirements for our infrastructure, ex:
🏎️ Hardware accelerators
⚙️ System & model configuration
📚 Specific libraries/dependencies
That’s why @cern.voxxeddays.ch I was honored to demo Ramalama.ai, a project that containers to safely run AI models 🤖
LLM Inference workloads are becoming monolithic, heavy, & hard to scale. That's where platform engineers can embrace llm_d, a new open-source effort that’s starting to tackle a problem we’re seeing more and more in prod ML stacks!!! 🎧 to @cedricclyburn.com & Christopher Nuland👇 to learn more
Thanks for having us mate!
Live from #KubeCon Europe in Amsterdam! 🇳🇱
Big announcement from the Red Hat booth: llm-d, a cloud-native way to run AI at scale with major performance & cost savings.
+ ran a workshop on RAG at scale using KubeFlow & Docling on Kubernetes. Slides below 👇
If you’ve seen my “silly slide” of all the open-source AI projects at past dev conferences, this week at #KubeCon we’re putting them together! Join me & friends for a hands-on workshop: build a sovereign RAG app on K8s with Kubeflow, Knative, Docling & vLLM. Wed 3/25 @ 11am 🚀
🔗 sched.co/2CW1f
Many folks compare whether “Opus 4.6 is better than ChatGPT 5.4” but there’s quietly been TONS of progress in the open source world of AI too (ex. #DeepSeek, #Llama) 🤖 with no rate limits, ads, and 100% local!
📰 Check out the article on @allthingsopen.bsky.social: allthingsopen.org/articles/run...
🖼️ Slides here: red.ht/mcp-deck
What does it look like to integrate #MCP into real enterprise workflows? This week at @devnexus.bsky.social we showed how to run, inspect, and scale agentic AI for debugging a Kubernetes clusters, diagnosing Ansible jobs, and much more!
Check out the slides below ⬇️ as well as the MCP servers used!
Can’t wait to be there in Prague soon!
Dev track is deploying heavy artillery.
Stop polyfilling frontend and duct-taping backend. Time to build stacks that scale.
The engineers: Switch Angel, @tej.as, @abtris.bsky.social, Krasimir Tsonev, @clytaemnestra.bsky.social, @utilitybend.com, @cedricclyburn.com, @ericwbailey.website & more.
With agentic coding tools like #ClaudeCode, #Cursor, and #Codex, how can you get the results you need from an LLM without spending all your time going back and forth about a wrong dependency or missing test cases 😆 well…
🎥 Spec-Driven Development: AI Assisted Coding Explained: youtu.be/mViFYTwWvcM
🤖 AI Agents are awesome… until they aren’t!
What just happened with an 🦞 OpenClaw (ClawdBot/MoltBot) agent in the Matplotlib project on GitHub shows the potential challenges with giving AI Agents (LLM + Tools + Reasoning) the ability to act autonomously. It’s why guardrails and auth are important!
Thanks for having us! It’s gonna be a great time learning all about using open source AI 🤖
Want to build fast? We’ve got the blueprints.
🔹 @lomagnette.bsky.social: Building Interoperable AI Agents in 30 mins.
🔹 @danieloh30.bsky.social, @cedricclyburn.com & Legare Kerrison: A crash course in Open Source AI.
🔹 @marianne-h.bsky.social: Unveiling the math behind it all.
AI sits to your right, but you're the captain
- @vilojona.bsky.social: Practical ways to keep AI codegen under control
- @vjovanov.bsky.social: Taming GraalVM with AI
- @timtebeek.github.io: Deterministic modernization in the AI age
- @kevindubois.com @cedricclyburn.com: Local development strategies
Thanks @devoxx.uk! Can’t wait to join @kevindubois.com in live-demo’ing how devs can code locally in the AI era using open source!
‼️‼️‼️
💻 Building with Open Source AI: red.ht/java-ai-workshop
Today kicks off @jfokus.se in Stockholm 🇸🇪 and we just delivered our workshop on building with open source AI models using:
⚡️ #vLLM serve local LLM’s as a local API endpoint
🦜 @langchain4j.dev for adding LLM capabilities in our Java application
Was a huge hit! Slides ⬇️
Automatizar tu vida con servidores MCP: integraciones, flujos y cómo conectar herramientas para que trabajen por ti ⚙️ Con @cedricclyburn.com en T3chFest 2026
Gracias!
I’m excited to bring #Ramalama, the container-native project to run AI models locally, to @cern.voxxeddays.ch 🙌
We’ll show how fast devs can spin up an open source model using their favorite container engine (shoutout @podmanio.bsky.social) for RAG (Q&A on PDF’s) and Agentic (calling API’s) 🤖
