Blog

ChatLLaMA 0.0.2 - Build your hyper-personalyzed ChatGPT assistant

Pierpaolo Sorbellini

•

March 12, 2023

Featured articles

How to increase GPU utilization in Kubernetes with NVIDIA Multi-Process Service (MPS)

Michele Zanotti

•

February 21, 2023

How does PyTorch 2.0 perform in inference? A benchmark with TensorRT and ONNX Runtime

Diego Fiori

•

December 4, 2022

Token Merging (ToMe) — Meta’s Optimization Technique to Make ViT Faster. But Can ViT be Even Faster?

Martina Fumanelli

•

February 17, 2023

Filter by topic

Efficient LLMs and Chatbots

Inference Optimization

AI infrastructure Optimization

Top 10 in AI

Efficient LLMs & Chatbots

META’s LLaMA: A small language model beating giants

META open-source model will help us to understand how LMs biases arise.

Salvatore Raieli

AI Infrastructure Optimization

How to increase GPU utilization in Kubernetes with NVIDIA Multi-Process Service (MPS)

Michele Zanotti

•

February 21, 2023

Dynamically partition GPUs in Kubernetes with NVIDIA Multi-Instance GPU (MIG)

Michele Zanotti

•

January 26, 2023

Automatically maximize the utilization of GPU resources in a Kubernetes cluster

Diego Fiori

•

January 22, 2023

Inference Optimization

Token Merging (ToMe) — Meta’s Optimization Technique to Make ViT Faster. But Can ViT be Even Faster?

PyTorch 2.0 Release: Summary of Updates and Improvements

Full Stack Optimization of Transformer Inference: a Survey. Part 1 on Bottlenecks and Hardware Implications

Accelerate YOLOv8 inference time by 4-6 times with Speedster