Adrian Boguszewski
where else to find them
no profile links on file
what they talk about
where they keep going back
- PyData Eindhoven2 editions2023–2024
on a stage with
who talks about the same things
- Dmitriy Pastushenkov3 talks
- Chris Fregly23 talks
- Aditya Lohia1 talk
- Vincent Caldeira16 talks
- Brian Rogers6 talks
- Merve Noyan11 talks
| title | conference | date |
|---|---|---|
| Cloud? No Thanks! I’m Gonna Run GenAI on My AI PC | PyData Eindhoven 2024 | 2024-07-11 |
Claims a single AI PC runs GenAI in seconds by combining CPU GPU and NPU and using the OpenVINO Toolkit to optimize models and reduce dependencies. Demos are… | ||
| Beyond the Continuum: The Importance of Quantization in Deep Learning | PyData Eindhoven 2023 | 2023-11-30 |
Quantization shrinks models and speeds inference with concrete gains: weight compression cuts LLaMA‑7B from 25 GB to 6 GB and Dolly from 44 to 11 GB… | ||
| Optimize your network inference time with OpenVINO | PyCon DE & PyData Berlin 2022 | 2022-04-11 |
Converts trained TensorFlow/Keras/PyTorch (via ONNX) models with the Model Optimizer into IR files (XML + BIN), applies optional post‑training quantization… | ||
| In the service of the history. AI in archivistics. | PyData Warsaw 2019 | 2019-12-12 |
A pipeline labels and recognizes faces on archival photos and ships as working prototypes, not slides. Trained on a long‑tailed set with 250k published and 37… | ||
| nothing matches | ||