vLLM community plans PyTorchCon talks in San Jose, October 20–21

AIInferact says it will attend PyTorchCon in San Jose, Oct 20–21, with talks and a booth at P1. It is co-hosting an Inference & RL Coffee Club with Anyscale and Nscale on Oct 20–21 from noon to 5 PM PT. The vLLM community is also presenting talks on attention, KV transfer, prefix caching, and the vLLM roadmap at the event.

AIThe vLLM community will attend PyTorchCon in San Jose on October 20–21, according to a post from vLLM's X account. Planned talks cover attention, KV transfer, prefix caching, and the vLLM roadmap. The post links to the conference schedule for attendees to plan their sessions.