Gian Paolo Santopaolo

Hands-On ML Engineering Meets Strategic Vision—Bridging Code and Cloud to Drive Enterprise AI for Real-World Impact

HOME
SERVICES
SOLUTIONS
TRAININGS
WORKSHOPS
PROJECTS
POSTS
ABOUT

Home Categories Inference

Category

Inference 1

Predict Peak VRAM Before Downloading a Model (Weights + KV Cache + Quantization) Jan 26, 2026

Recently Updated

Predict Peak VRAM Before Downloading a Model (Weights + KV Cache + Quantization)
PyTorch Training Loop: A Production-Ready Template for AI Engineers
Why GPUs Love Tensors: Understanding Tensor Cores and AI Acceleration
Tensor Parallelism in Transformers: A Hands-On Guide for Multi-GPU Inference
Choosing the Right Loss Function for your ML Problem

Trending Tags

Data Visualization MNIST fine-tuning trl asitop Batch Size cost function Epochs Hyperparameters Learning Rate

© 2026 Gian Paolo Santopaolo. Some rights reserved.

Opinions expressed in this website are my own.

Trending Tags

Data Visualization MNIST fine-tuning trl asitop Batch Size cost function Epochs Hyperparameters Learning Rate

A new version of content is available.