milesial repositories

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Last commit Sep 1, 2021

Personal experimentation with Deep-Q-Networks for reinforcement learning

Last commit Apr 9, 2018

Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material design, drug discovery, etc.

Last commit Jun 22, 2022

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Last commit May 30, 2026

AI Toolkit for Healthcare Imaging

Last commit Feb 20, 2023

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

Last commit May 4, 2026

NeMo: a toolkit for conversational AI

Last commit Jan 10, 2023

Participation in the 2018 PLAsTiCC Astronomical Classification from Kaggle

Last commit Nov 25, 2018

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

Last commit Jun 5, 2023

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.

Last commit Aug 21, 2025

Offline optimization of your disaggregated Dynamo graph

Last commit Apr 28, 2026

AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.

Last commit May 5, 2026

Last commit Jan 20, 2023

Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

Last commit Dec 19, 2025

Dockerized Jupyter kernels.

Last commit Nov 10, 2022

A Datacenter Scale Distributed Inference Serving Framework

Last commit Jun 5, 2026

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

Last commit Mar 10, 2022

Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.

Last commit Sep 4, 2025

No recent commit data

Machine learning metrics for distributed, scalable PyTorch applications.

Last commit Feb 6, 2023