vLLM Meetup Toronto

​Join us for the vLLM x Cohere meetup in Toronto, an evening for AI engineers, researchers, and infrastructure builders.

​This is a chance to connect with vLLM maintainers, the Cohere team building and serving models for production-scale workloads, and engineers working on inference at NVIDIA. We'll cover how the vLLM ecosystem and Cohere's open-weights work and upstream contributions fit together.

​The session goes deep on inference, including the vLLM roadmap, speculative decoding, serving for agentic workloads, and scaling agentic RL. We'll close with a live panel on where inference is heading and what's next for open source AI, then finish the evening with networking, drinks, and bites.

​Speakers

• ​Roger Wang, Co-founder, Inferact; Core Maintainer, vLLM

• ​Ekagra Ranjan, Member of Technical Staff, Cohere

• ​Sungjin Hong, Machine Learning Engineer, Cohere

• ​Zhanda Zhu, System Software Engineer, NVIDIA; CS PhD, University of Toronto

• ​Kosseila Hd, Lead Forward Deployed Engineer, Tensormesh

​Schedule

• ​6:00pm - Doors open

• ​6:30pm to 8:00pm - Talks and panel Q&A

• ​8:00pm to 9:00pm - Networking reception