Exploring 15x Faster AI Inference with Cerebras Wafer-Scale Engine – Toronto Event on Sept 28

Join us for a cozy evening exploring the cutting edge of AI inference speed, pizza, conversation, and show & tell. Come curious and ready to see what's next. All attendees will get free Codex and Cerebras credits to build with on the night (and beyond). You'll get a firsthand look at Cerebras Inference, powered by the 𝗪𝗮𝗳𝗲𝗿-𝗦𝗰𝗮𝗹𝗲 𝗘𝗻𝗴𝗶𝗻𝗲 𝟯, delivering up to 𝟭𝟱𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 𝗔𝗜 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝘁𝗵𝗮𝗻 𝗹𝗲𝗮𝗱𝗶𝗻𝗴 𝗚𝗣𝗨𝘀 — and talk through what that speed unlocks for product experiences, roadmaps, and what to prioritise next. We'll be joined by 𝗚𝗼𝗹𝗮𝗿𝗮 𝗔𝘇𝗮𝗿, 𝗚𝗲𝗻 𝗔𝗜 𝗦𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁, for a quick intro, Q&A, and a look at how fast inference is reshaping what's possible to build. 📍 Toronto 🗓️ September 28, 6:30 to 8:30 p.m. luma.com/cafecomputetoronto