Helsinki MLOps Meetup | Maria 01
Starting the year right with an evening of technical deep-dives, followed by drinks and conversation with the local ML community.
We’re hosting at our Maria 01 office, and we’ve got two solid technical talks lined up:
Riccardo Mereu, ML Engineer @ Verda Unlocking FP4: Low-Precision AI on NVIDIA Blackwell
Riccardo will walk through FP4 on NVIDIA Blackwell Ultra, covering why low-precision formats matter for scaling AI workloads and sharing hands-on insights from working directly with Blackwell Ultra GPUs.
Shantipriya Parida, Senior AI Scientist @ AMD Silo AI LLM Compression: Balancing Size and Performance
Shantipriya will break down key quantization techniques and explore how model compression can reduce inference costs and model size while maintaining performance with practical takeaways for production ML systems.
After the talks, we’ll have drinks and food while you connect with other ML engineers and researchers in Helsinki.