vLLM Conference Happy Hour: Hosted by AMD and Inferact

Cap off day 1 of the first vLLM Conference with drinks, food, and the people who build the AI stack. Join builders from AMD, Inferact and the vLLM community, for casual conversation about open models, inference performance, and where the hardware is headed.

Who you'll meet

Inferact is the company founded by the creators and core maintainers of vLLM, leading the vLLM roadmap and building the future of inference.

AMD builds the industry leading accelerators that a growing share of the world's inference runs on, working with the Inferact / vLLM team to ensure optimized inference via the ROCm ecosystem.

The format is a casual happy hour: come for the drinks, stay for the ideas, leave with new connections. No conference ticket required, and spots are limited.

Schedule

• 6:00pm — 9:00pm

Note: a government-issued ID is required for check-in.