milesial

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

A Python implementation of U-Net that automatically draws precise outlines around objects in photos, originally tested on car images from a Kaggle competition but adaptable to medical scans and portraits.

Free pass auto-refresher for xfinity hotspots

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A Datacenter Scale Distributed Inference Serving Framework

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

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

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.

Offline optimization of your disaggregated Dynamo graph

A high-throughput and memory-efficient inference and serving engine for LLMs

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

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.

NeMo: a toolkit for conversational AI

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.

Development repository for the Triton language and compiler

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

The Triton backend for the ONNX Runtime.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

No description.

No description.

Machine learning metrics for distributed, scalable PyTorch applications.

AI Toolkit for Healthcare Imaging

Enabling PyTorch on Google TPU

No description.

Benchmark datasets, data loaders, and evaluators for graph machine learning

Dockerized Jupyter kernels.

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.

Node.js JavaScript runtime :sparkles::turtle::rocket::sparkles:

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

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

Yet another online markdown editor

A tool and library for rotating your password on online services

Participation in the 2018 PLAsTiCC Astronomical Classification from Kaggle

Personal experimentation with Deep-Q-Networks for reinforcement learning

Transfer learning in tensorflow for Kaggle's challenge