Alberto Danese

Eseguire LLM e ML in locale è ormai pratico, ma mancano numeri comparabili sulle prestazioni reali. Presento una suite Python open source che misura la velocità di inferenza LLM e di training tabulare, più una pipeline end-to-end a 0€ per raccogliere e pubblicare i risultati della community.

When you talk dataframe in Python, you talk Pandas. Many alternative libraries in the last decade have tried to dethrone it, with little or no success. Polars has all it takes to be pose a serious challenge: amazing speed, an intuitive API, a growing community. Time to give it a try!

AWS offers many choices for solving business problems through machine learning (ML), ranging from built-in algorithms, frameworks, and more in ML services down to models and algorithms available via AWS Marketplace. Amazon SageMaker supports 17 built-in ML algorithms, such as classification, regression, and recommendation.