Speculative Decoding in Production Panel w/ Baseten, Cohere, Rootly and Wealthsimple
New models are bigger and more capable than ever, and serving them fast, reliably, and affordably is one of the hardest problems in AI engineering.
Join Baseten and Rootly in Toronto for an evening with engineers who run LLM inference in production every day. Our panel will cover speculative decoding and the other techniques teams use to make models faster, along with what actually matters once real customer traffic hits.
Topics:
How speculative decoding works, and when it’s worth it
What’s changed now that newer models ship with strong speculators out of the box
Tuning inference performance for specific customer workloads
Keeping LLM systems reliable in production when things break
Panelists
Jessie Lamontagne, Senior Manager, Data Science, Wealthsimple
Sepideh(Sep) Shaterian, Member of Technical Staff, Cohere
Sylvain Kalache, Head of AI Labs, Rootly
Daniel Buades Marcos, Engineering Manager, Forward Deployed Engineering, Baseten
More speakers to be announced
Schedule
6:00–6:30 PM: Welcome drinks and snacks
6:30–7:30 PM: Panel and Q&A
7:30–8:00 PM: Wrap up and networking
📍 Rootly Toronto - 366 Adelaide St W, Unit 601
🗓 Thursday, November 19th
About Baseten
Baseten is an inference infrastructure provider that specializes in high-scale, customer-facing workloads. The Baseten Inference Stack enables engineering teams to performantly, scalably and cost-effectively serve AI models in production without having to worry about AI infrastructure. Security and compliance is baked into the stack and deployments can be done in any region and on any cloud. With Baseten, developers can focus on building their product with the confidence that they will always deliver the optimal user experience.
About Rootly AI
Rootly AI is the AI-native on-call and incident response platform that provides proactive support to help Site Reliability Engineers resolve incidents faster, improve system resilience, and streamline on-call operations. It’s your always-on SRE copilot that automates root cause analysis and identifies patterns that drive continuous improvement—trusted by hundreds of companies like LinkedIn, NVIDIA, Replit, Elastic, Canva, Clay, Tripadvisor, and Shell.