Pruna's AI Efficiency Meetup #3 - Paris Edition

​Welcome to this month's AI Efficiency meetup.

​​Join AI developers, ML engineers, and researchers for a monthly evening filled with technical deep dives, live demos, and cutting-edge insights into making AI systems faster, leaner, and more cost-effective.

​​This meetup is designed for those scaling LLMs, fine-tuning diffusion models, or deploying real-time inference pipelines.

​​This is an excellent opportunity to learn and share! We will cover practical strategies, cool new tools, and conversations from research to real-life struggles.

​​🗓 Agenda:

​7 pm: Welcome!

​7:30 pm – 8:15 pm: Talks

• ​James Martin "AI's Impacts: How to explain the problems, & above all the solutions" - Better Tech, Founder

• ​Jules Belveze "Early Exiting: Under Hyped Compression Methods" - Dust, Software Engineer

• ​Amine Saboni "Why quantization works?" - Pruna AI, MLOps

​8:15 pm - 9 pm: Networking & Food.

​9 pm: End of the event.

​🎤 Speaker: Apply here to submit a talk.

​​📍Location: Paris 9th, the event location will be shared with approved guests.

​​🔥 Spots are limited!