Huamin Chen

[vLLM Office Hours #34] AI-Powered vLLM Semantic Router - October 09, 2025 x.com/i/broadcasts/1…

When to Reason: Semantic Router for vLLM. arxiv.org/abs/2510.08731

Next Thursday, October 3, join us for bi-weekly @vllm_project office hours to learn about the new AI Powered vLLM Semantic Router. GitHub: github.com/vllm-project/s… Register for office hours: red.ht/office-hours

Talks and demos will include: • Getting started w/ vLLM — @wattsteve (PyTorch ambassador) • Intermediate vLLM: PagedAttention, quant, spec decode, continuous batching — @luka_govedic (vLLM core) • vLLM Semantic Router — Huamin Chen @root_fs (project creator) • Scaling w/ llm‑d — Greg Pereira (maintainer)

New on the Red Hat Developer blog: vLLM Semantic Router – Improving Efficiency in AI Reasoning An open source router that sends the right query to the right model, reducing cost and latency while maintaining accuracy. Read here: developers.redhat.com/articles/2025/…

Austin friends - we’ve got something special coming up on Wednesday, September 17 at @CapitalFactory! PyTorch ATX + vLLM are teaming up for a joint meetup. Over 200 folks are already signed up, and there’s still a few spots left. Come hang out, learn, and meet others building with LLMs. Here’s what’s on the agenda: 1⃣ Getting started with vLLM inference - Steve Watt, PyTorch ambassador (@wattsteve) 2⃣ Intermediate vLLM: PagedAttention, quantization, speculative decoding & more - Luka Govedič, vLLM committer (@luka_govedic) 3⃣ Semantic Router: Auto-reasoning router for efficient mixture-of-models inference – Huamin Chen, project creator (@root_fs) 4⃣ Scaling vLLM with Kubernetes + llm-d - Greg Pereira, maintainer Sign up here: meetup.com/pytorch-atx/ev… Please help us share the event 🙏

Next up in emerging tech - @somalley108 shows us how she uses Project Kepler to monitor power consumption in resource-constrained edge devices: red.ht/46VE1R6

In this episode of Technically Speaking with @kernelcdub, we explore the possibilities of more sustainable #cloudnative workloads with @KeplerProject and its co-founder @root_fs. Watch Now: red.ht/45kLZSd

@sebi2706 @SimonHiker friends of kepler will help friends using kepler :D please open GH issue when you hit one

@SimonHiker I would like to demo it for a keynote I’m giving in 15 days , I want to show a practical use case of eBPF , show how good workloads can affect consumption. But no luck so far to run it locally with Kind , I probably need a real cluster.

Yay my pods do not consume any energy !! *Narrator voice* : Kepler operator was not able load the eBPF modules and therefore not report any metrics

What's next in green computing? @piparul and @root_fs explain the ins and outs of Project Kepler, the CNCF sandbox project that is bringing power monitoring to Kubernetes and beyond! red.ht/45Fuo7U

The five steps to deploy #cloudnative sustainable foundation #AI models starts with the obvious two: #containers to manage the workloads and #Kubernetes to deploy across a distributed infrastructure. We talked about all the steps with @root_fs of @redhat. bit.ly/3NByE15

Kepler in #CNCF sandbox now lists.cncf.io/g/cncf-toc/mes…

@johanngyger @CaraDelia @root_fs Absolutely agree, I can say at least the folks talking today genuinely care. On the Microsoft and Azure side, we're doubling down in this space, more right after this and throughout summer!

#issuecomment-1514168286" target="_blank" rel="nofollow noopener">github.com/kedacore/keda/… #CloudNativeCon #kedacore #Sustainability

Get ready to explore sustainable computing with Kepler - the Kubernetes-based Efficient Power Level Exporter! Listen to an insightful conversation with @root_fs on Cloud7's Red Hat series. #sustainablecomputing #Kepler #Kubernetes cloud7.news/podcasts/susta…

@root_fs of #redhat talks Project Kepler and measuring power usage at #KubeCon

Accelerate Sustainable Computing with Community Collaboration - Cara Delia, Principal Community Architect Financial Services and Sustainability, Red Hat & Huamin Chen, Senior Principal Software Engineer, Red Hat at KubeCon + CloudNativeCon Europe 2023 sched.co/1HyPf

THIS WEDNESDAY is the next meeting. We will have Kepler (github.com/sustainable-co…) presenting for the first half hour followed by KubeCon prep discussions.

At #MobileWorldCongress, Red Hat and IBM Research launched an open source project to capture power usage metrics from #Kubernetes clusters. containerjournal.com/features/red-h…

Great to get an impromptu briefing from @RedHat on how operators are able to deploy K8S packaged workloads to the far edge using Microshift, Podman or OpenShift. Will hopefully be getting more details. #MWC23 #redhat