Miguel Martínez's repositories
ai--transfer-learning-for-image-classification
This repository contains the 'transfer learning for image classification' project of the Udacity's AI Programming with Python Nanodegree Program.
machine-learning-engineer-nanodegree
Udacity's Machine Learning Engineer Nanodegree
react-nanodegree
Udacity's React Nanodegree
artificial-intelligence-nanodegree
Udacity's Artificial Intelligence Nanodegree + Specializations (CV and NLP)
computer-vision-nanodegree
Udacity's Computer Vision Nanodegree
natural-language-understanding-xcs224u
Stanford NLU
self-driving-car-engineer-nanodegree
Udacity's Self-Driving Car Engineer Nanodegree
CUDA-Training-Series
Training materials associated with NVIDIA's CUDA Training Series (www.olcf.ornl.gov/cuda-training-series/)
FasterTransformer
Transformer related optimization, including BERT, GPT
Megatron-LM
Ongoing research training transformer models at scale
model_analyzer
Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.
nemo-curator
Scalable toolkit for data curation
NeMo-Megatron-Launcher
NeMo Megatron launcher and tools
notebooks-contrib
RAPIDS Community Notebooks
nvaitc-toolkit
Open source code base to showcase interoperability of CUDA-X AI software stack in multi-GPU environments and thus provide researchers a reference framework to build new projects on.
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.