Uploaded September 2026 | Updated November 2026, 2 days ago
Agentic production traffic brings long multi-turn sessions, heavy prefix reuse, and bursty, heterogeneous requests that challenge conventional serving.
At Ray Summit 2026, Yifan Qiao and Zijing Liu from Inferact explain how vLLM addresses those patterns through independently scaled prefill/decode disaggregation, turn-aware serving, and session and correlation hints that improve prefix caching, prefetching, and eviction. They also cover distributed KV cache transfer and storage with Mooncake and multi-tier offloading, allowing cached context to move across turns and instances instead of being recomputed.
You'll leave with practical guidance for architecting and tuning vLLM deployments for production agents.
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
Agentic production traffic brings long multi-turn sessions, heavy prefix reuse, and bursty, heterogeneous requests that challenge conventional serving.
At Ray Summit 2026, Yifan Qiao and Zijing Liu from Inferact explain how vLLM addresses those patterns through independently scaled prefill/decode disaggregation, turn-aware serving, and session and correlation hints that improve prefix caching, prefetching, and eviction. They also cover distributed KV cache transfer and storage with Mooncake and multi-tier offloading, allowing cached context to move across turns and instances instead of being recomputed.
You'll leave with practical guidance for architecting and tuning vLLM deployments for production agents.
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










