9 Nov 2026 Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM
WebAssembly and Tornado VM enable efficient local inference, while LLMD optimizes distributed GPU usage and semantic routing for on-premises AI deployment.
More Podcasts by InfoQ episodes

Published 16 Mar 2026
Duration: 00:31:33
Discusses challenges in AI deployment from proof-of-concept to production, introduces JReleaser's multi-language release automation with digital signatures and cross-platform integrations, highlights the Common House Foundation's open-source support and regulatory adaptations, and explores automation, cloud integration, and community-driven maintenance strategies for project sustainability.
Andres Almiray, a serial open-source contributor and the creator of JReleaser, discusses the project's state, noting that the tool is usable across an...
The podcast discusses challenges in deploying AI systems effectively, highlighting a common engineering gap between proof-of-concept development and reliable production implementation. A focus on open-source collaboration is emphasized through the interview with Andres Almire, a Java champion with 20 years of open-source experience. His work includes tools like JReleaser, a CLI for cross-language software releases, which addresses security in supply chains and aligns with Europes Cyber Resilience Act. JReleasers roadmap includes a 2-month release cycle, multi-language support (Java, Rust, Go, etc.), and a debate over rebranding to reduce confusion about its Java-centric origins. Key updates include expanded digital signature support, package manager integration (Homebrew, Docker), and plans to simplify release automation by reducing manual steps and legacy features. The tool also introduces a "YOLO" flag for experimental workflows and a flexible DSL for configuration, with ongoing efforts to streamline usability and governance.
The discussion extends to open-source projects hosted by the Common House Foundation, including tools like Jarleser, Quarkos, and SlateDB, which aim to support sustainable development across languages. The foundation promotes low-governance models, prioritizing project autonomy while addressing challenges like succession planning, sponsorship, and compliance with regulations such as Europes Cyber Resilience Act. Topics like cloud integration, where CLI help menus can infer capabilities, and the role of large language models (LLMs) in generating DSL configurations are also covered. The podcast underscores the importance of community-driven solutions, with initiatives to engage new contributors through low-pressure tasks, GitHub discussions, and collaborative events.
Future directions include improving JReleasers ecosystem by reducing dependency on tool-native alternatives and aligning its roadmap with user needs. The tools 2.0 version may introduce breaking changes, such as replacing custom announcers with a generic webhook system, while refining its DSL for clarity. The Common House Foundation also seeks sponsors to support project growth and sustainability, emphasizing financial transparency and community-led governance. Overall, the conversation highlights the evolving landscape of open-source development, balancing technical innovation with collaborative practices, regulatory compliance, and user-centric design.
9 Nov 2026 Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM
WebAssembly and Tornado VM enable efficient local inference, while LLMD optimizes distributed GPU usage and semantic routing for on-premises AI deployment.
2 Nov 2026 Educating an Architect: A Conversation with Luca Mezzalira
Architects must evolve from technical designers to social-technical enablers, using domain-driven design to balance AI automation with human oversight in core systems.
12 Oct 2026 What Does It Really Mean To Program With AI: A Conversation with Joy Ebertz
"Explores software architects' evolving role in balancing technical and business challenges, AI's impact on modular architectures, risks of automation, and the need for human oversight in AI-assisted development."
5 Oct 2026 Future Cybersecurity: Hardware Memory Safety, Automated Governance and Post-Quantum Cryptography
"Challenges and advancements in AI, security, and software development are discussed, emphasizing governance, open-source maintenance, hardware security, automation, and regulatory compliance like the EU's Cyber Resilience Act, alongside post-quantum cryptography and AI's dual role in security."
28 Sept 2026 The AI Revolution Fails Without Psychological Safety For Developers: A Conversation with Erin Doyle
"Software architects must adapt to AI-driven shifts in system design, balancing automation with human oversight, team alignment, and ethical considerations in modern development."