Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models.
Related
ramyadharshinimurugaprakash-commits/Titanic-Survival-Prediction-Random-Forest: A machine learning project that predicts passenger survival on the Titanic using the Random Forest Classifier. The project includes data preprocessing, label encoding, feature scaling, model training, prediction, and performance evaluation using Python and Scikit-learn.
A machine learning project that predicts passenger survival on the Titanic using the Random Forest Classifier. The project includes data preprocessing, label encoding, feature scal...
Yang-bioinfor/diffusion_anomaly: Reproduction of Diffusion Models for Medical Anomaly Detection
Reproduction of Diffusion Models for Medical Anomaly Detection