Maintainers
5Project-wide owners who set engineering direction, approve releases, resolve technical escalations, and steward repository access.
Building the Mixture-of-Models for the next era of computing.
Long-term incubator of frontier infrastructure and AI systems across cloud-native platforms, open-source ecosystems, and model-serving stacks.
Software engineer building AI infrastructure for large-scale LLM serving and agents, with a background in computer vision.
Senior software engineer building enterprise AI agents, GSoC mentor, and AsyncAPI Technical Steering Committee member.
Cloud-native contributor working on Kubernetes orchestration and LLM serving across Karmada, Volcano, and Kthena. LFX mentor for Kthena.
Committers
16Active trusted contributors who review changes, own implementation areas, triage issues, and keep the project moving.
Software engineering intern at Quid and graduate student at National Taiwan University, focused on machine learning systems. An Apache Airflow and Apache TVM Committer and PyTorch Collaborator.
Software engineer at Barclays building reliable backend services. Contributes to open-source infrastructure for LLMs and AI agents, with a focus on system design and production reliability.
Forward Deployed Engineer at Rebellions, combining machine learning engineering and solution architecture to bring LLM inference to NPUs.
Software engineer working on distributed storage at Nutanix, with interests in LLM inference, model serving, and intelligent request routing.
Software and data engineer studying at NYU, focused on scalable systems and data pipelines. Contributes to Apache Hudi and has worked on SQLancer through Google Summer of Code.
Co-founder and CTO of KR Labs, working on open-source NLP tools for transparent and trustworthy AI. His experience spans academic research and production NLP systems.
GTM Tech Lead at Google.
DaoCloud engineer and open-source contributor focused on practical infrastructure improvements.
Computer science engineer at Intuit focused on software systems.
Open-source contributor to vLLM Semantic Router.
AI researcher and software engineer working across AI for science, LLM systems, agentic infrastructure, and computer vision.
Cloud-native and AI engineer building enterprise solutions and open-source AI infrastructure.
Software engineer focused on large-scale recommendation systems, backend engineering, LLM deployment, and inference.
Works across AI, agent, and data infrastructure, with recent work in vLLM, Ray, and data systems.
Kata Containers maintainer working on Kubernetes and container infrastructure.
Open source contributor to vLLM Semantic Router.
Emeritus Committers
22Former active committers recognized for their contributions. This roster is refreshed from GitHub activity over the rolling three-month window from to .
Open-source contributor to vLLM Semantic Router.
Senior Staff Research Scientist at IBM, focusing on advanced AI systems and research.
Staff Research Scientist at IBM, specializing in AI research and LLM Inference.
A dynamic and hands-on Engineering Manager who thrives on building elite engineering teams and driving them to deliver exceptional results.
Making life easier for developers and customers through innovative tooling. From the Red Hat Office of the CTO.
Cloud-native AI infrastructure product leader. Focused on Kubernetes, GPU resource scheduling, and large-scale LLM serving platforms.
Software engineer, focused on backend and cloud-native systems, with hands-on experience exploring AI infrastructure, LLM-based systems, and RAG architectures.
Senior software engineer with a research-driven mindset, specializing in cloud-native platforms, Kubernetes-based infrastructure, and AI enablement.
Software engineer with a research-driven mindset, focused on cloud-native platforms and AI infrastructure. Open-source contributor.
Software engineer with a research-driven mindset, focused on cloud-native platforms and AI infrastructure. Open-source contributor.
Open source contributor to vLLM Semantic Router.
Open source contributor to vLLM Semantic Router.
Software engineer with a research-driven approach, focused on cloud-native platforms and AI infrastructure. Building semantic routing systems and contributing to open-source LLM orchestration projects.
Software engineer with a research-driven approach, focused on cloud-native platforms and AI infrastructure. Building semantic routing systems and contributing to open-source LLM orchestration projects.
Application software engineer with experience in Distributed Control Systems and Big data.
Open Source Engineer at DaoCloud, focusing on container technology and cloud-native solutions. Passionate about contributing to vllm and other open source projects.
Senior Software Engineer @ Kong Inc. | Microsoft MVP | CNCF Ambassador | Kubernetes Ingress-NGINX maintainer | PyCon China & KCD Beijing organizer.
Open source contributor to vLLM Semantic Router.
Open source contributor to vLLM Semantic Router.
Open source contributor to vLLM Semantic Router.
Open source contributor to vLLM Semantic Router.
Open source contributor to vLLM Semantic Router.