博客

The Triton TensorRT-LLM Backend

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Transformer related optimization, including BERT, GPT

Mesh TensorFlow: Model Parallelism Made Easier

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

分享一下鄙人自己做的一些特效字幕，如有写得不当的地方还请多多包涵。

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

CUDA Library Samples

Ongoing research training transformer models at scale

Efficient Top-K implementation on the GPU

Dota 2 Python AI

Dota2 AI Framework

Patterns and behaviors for GPU computing

A toolkit for developing and comparing reinforcement learning algorithms.

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

Tutorials for building a PySC2 bot

An elegant PyTorch deep reinforcement learning library.

Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学

This is the code for "OpenAI Five vs DOTA 2 Explained" By Siraj Raval on Youtube

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Tutorials for creating and using ONNX models

ONNX-TensorRT: TensorRT backend for ONNX