We are very happy to invite you to 37th edition of PyData Trójmiasto meetup!
Where: Łużycka 8B, Gdynia, Tensor Z building.
When: 29th of October at 6PM
Registration: please register with your full first and last name. Don't forget to bring your ID when entering the event venue.
RSVP available until 6pm day before. In any urgent communication please let us know at kontakt@pydata-trojmiasto.pl
Parking: Free parking located along the street next to the building.
Agenda:
18:00 - 18:05 - Event boarding
18:05 - 18:10 - A few words about PyData
18:10 - 18:55 - Modeling cities with build123d library by Marta Sienkiewicz
19:00 - 19:45 - WTF is Temperature: LLM inference in Practice by Dariusz Piotrowski
19:45 - Networking & snacks
About "Modeling cities with build123d library" by Marta Sienkiewicz:
In her presentation she will show you a script in Python that combines some of her interests: urban planning and 3D modeling. You will learn how you can generate a 3D model of a city using Python, build123d library and OpenStreetMap data. If this is your first encounter with 3D modeling in Python, you may be surprised how simple the script actually is.
Marta works at Hapag-Lloyd as an IT Release Manager. In her spare time she particularly enjoys meeting with fellow technology enthusiasts in Hackerspace Trójmiasto.
About "WTF is Temperature: LLM Inference in Practice" by Dariusz Piotrowski:
Ever wondered what actually happens when you call an LLM API? This talk breaks down the inference pipeline from tokenization to text generation, explaining what's really going on under the hood.
He will walk through the key sampling strategies and their parameters - temperature, top-p, top-k, beam search. We'll also cover performance tricks like quantization, KV caching, and prompt caching that can speed things up significantly. If time allows, we will also touch on some use-case-specific techniques like pass@k and majority voting.
After spending 4 years as Applied Scientist at Amazon, where he worked on Text to Speech (TTS) for Alexa and Computer Vision (CV) for Ring he began to work for the past 2 years as a Senior Machine Learning Engineer (contractor) including last half a year for Amazon Robotics dedicating his time and skill to build a neuro-symbolic planning systems.
