vLLM x Cohere Toronto meetup to cover roadmap, speculative decoding and scaling agentic RL
cohere · x · 2026-10-03
Cohere published the registration page for its Toronto meetup with vLLM, aimed at AI engineers and infrastructure builders. The agenda covers the vLLM roadmap, speculative decoding, serving agentic workloads, and scaling agentic RL, closing with a panel on open-source AI's future. Speakers include vLLM lead maintainer Roger Wang plus engineers from Cohere, NVIDIA, and Tensormesh.
Related event: Cohere and vLLM to Host Open Inference Meetup in Toronto(2 posts)→
More from Companies & People
- First NECB2026 draws 360+ researchers, 190+ abstracts over two days — KevinKaichuang · 2026-10-03
- Roche LLM team member to start new role on Nov 2 — sjmielke · 2026-10-03
- Ex-Genentech LLM eval engineer kicks off thread on drug-discovery evaluation work — sjmielke · 2026-10-03
- Emad Mostaque predicts Anthropic will be "absolutely smashed" within two years as models commoditize — markjeffrey · 2026-10-03
- Stanford HAI's James Landay on educating lawmakers and shaping AI with people at the center — StanfordHAI · 2026-10-03
- Kevin Roose talks AGI with Walter Isaacson, says he used an Isaacson agent to edit his book — kevinroose · 2026-10-03