Uploaded September 2026 | Updated November 2026, 4 days ago
Four focused lightning talks explore systems work for production agentic workloads.
At Ray Summit 2026, Tun Jian Tan of Embedded LLM covers Agentic API, Jeffrey Wang of Anyscale discusses KV-cache-aware serving with Ray Serve LLM, Danny An of Novita presents human-AI collaboration between agents and engineers, and Ananth Mahadevan of Verda shares lessons learned from serving GLM-5.2 and Kimi K3 in production.
You'll leave with four rapid-fire perspectives on running agents in production.
This session was part of the first vLLM Conference at Ray Summit, hosted by Inferact.
Liked this video? Check out other Ray Summit vLLM session recordings: youtube.com/playlist?list=PLXMguE8Nc9o4
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
đź”— Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com
Four focused lightning talks explore systems work for production agentic workloads.
At Ray Summit 2026, Tun Jian Tan of Embedded LLM covers Agentic API, Jeffrey Wang of Anyscale discusses KV-cache-aware serving with Ray Serve LLM, Danny An of Novita presents human-AI collaboration between agents and engineers, and Ananth Mahadevan of Verda shares lessons learned from serving GLM-5.2 and Kimi K3 in production.
You'll leave with four rapid-fire perspectives on running agents in production.
This session was part of the first vLLM Conference at Ray Summit, hosted by Inferact.
Liked this video? Check out other Ray Summit vLLM session recordings: youtube.com/playlist?list=PLXMguE8Nc9o4
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
đź”— Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com










