Devoxx UK @devoxx.uk · Apr 22 1 / 2
Scaling AI on Hybrid Cloud for Production LLM Inference at Scale by Roberto Carratalá devoxx.co.uk/talk/?id=35453 Java Perf IRL: 5x Faster Cassandra Compaction by Nitsan Wakart devoxx.co.uk/talk/?id=6686
2 likes 1 replies
?
Replies
The Real Cost of a Token: Unmasking the Environmental Footprint of GenAI by Pietro Mele devoxx.co.uk/talk/?id=18382 How we made our team do stand-up on Minecraft (and you can too!) by Sawyer Bowerman devoxx.co.uk/talk/?id=34152