milesial 的仓库

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

最近提交 2021年9月1日

Personal experimentation with Deep-Q-Networks for reinforcement learning

最近提交 2018年4月9日

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.

最近提交 2022年6月22日

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

最近提交 2026年5月30日

AI Toolkit for Healthcare Imaging

最近提交 2023年2月20日

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.

最近提交 2026年5月4日

NeMo: a toolkit for conversational AI

最近提交 2023年1月10日

Participation in the 2018 PLAsTiCC Astronomical Classification from Kaggle

最近提交 2018年11月25日

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

最近提交 2023年6月5日

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.

最近提交 2025年8月21日

Offline optimization of your disaggregated Dynamo graph

最近提交 2026年4月28日

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

最近提交 2026年5月5日

最近提交 2023年1月20日

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

最近提交 2025年12月19日

Dockerized Jupyter kernels.

最近提交 2022年11月10日

A Datacenter Scale Distributed Inference Serving Framework

最近提交 2026年6月5日

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

最近提交 2022年3月10日

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.

最近提交 2025年9月4日

没有最近提交数据

Machine learning metrics for distributed, scalable PyTorch applications.

最近提交 2023年2月6日