Jiwei Liu

nvidia-kaggle. NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather competition context, study public writeups and notebooks, reproduce kernels locally, submit to competitions, and manage Ka

orbit_wars. Python

kvpress. LLM KV cache compression made easy

Curator. Scalable data pre processing and curation toolkit for LLMs

tinygrad. You like pytorch? You like micrograd? You love tinygrad! ❤️

tiny-gpu. A minimal GPU design in Verilog to learn how GPUs work from the ground up

Fuser. A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

lm-format-enforcer. Enforce the output format (JSON Schema, Regex etc) of a language model

Diversity-Sampling. GPU-accelerated algorithm for subsampling datasets while preserving diversity

tensorrtllm_backend. The Triton TensorRT-LLM Backend

ChatRTX. A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

TensorRT-LLM. 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. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

FasterTransformer. Transformer related optimization, including BERT, GPT

CoAtGIN. CoAtGIN: Marrying Convolution and Attention for Graph-based Molecule Property Prediction

catboost. A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

cuda-python. CUDA Python: Performance meets Productivity

arrow. Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics

cython-bind-c-example-2020. It shows you how to create a package with cython and c/cpp.

genedisco. GeneDisco is a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

neurips2021_multimodal_topmethods. Python

GLUE. Graph-linked unified embedding for single-cell multi-omics data integration

neurips2021_multimodal_viash. R

scanpy. Single-cell analysis in Python. Scales to >100M cells.

NVTabular. NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

stylegan2. StyleGAN2 - Official TensorFlow Implementation

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

stylegan. StyleGAN - Official TensorFlow Implementation

ALAE. [CVPR2020] Adversarial Latent Autoencoders

raft. RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

rapids-ai-BBO-2nd-place-solution. Python

bbo_challenge_starter_kit. Starter kit for the black box optimization challenge at Neurips 2020

TuRBO. Python

cupy. NumPy & SciPy for GPU

gpytorch. A highly efficient implementation of Gaussian Processes in PyTorch

dask-ml. Scalable Machine Learning with Dask

bayesmark. Benchmark framework to easily compare Bayesian optimization methods on real machine learning tasks

lofo-importance. Leave One Feature Out Importance

agents. TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

tpu. Reference models and tools for Cloud TPUs.

plotly-dash-rapids-census-demo. Jupyter Notebook

d2l-en. Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

gpu-bdb. RAPIDS GPU-BDB

ProbabilisticDeepLearningTensorFlow. Material for ODSC Europe presentation -- Probabilistic Deep Learning in TensorFlow, the why and the how

ALAE. [CVPR2020] Adversarial Latent Autoencoders

treelite. Universal model exchange and serialization format for decision tree forests

dask-glm. Python

rapids-kaggle-utils. High level utility functions for using Rapids on Kaggle Competitions

RAPIDS-development. Jupyter Notebook

cusignal. cuSignal - RAPIDS Signal Processing Library

HRNet-Semantic-Segmentation. The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

champs-scalar-coupling. Gold medal #2 Kaggle "Predicting Molecular Properties" compatition

PA-Graph-Transformer. Python

deeplearning. Jupyter Notebook

notebooks-contrib. RAPIDS Community Notebooks

fastai. The fastai deep learning library

kaggle-plasticc. 14th place solution for the Kaggle Plasticc challenge to classify objects in space.

cudf. cuDF - GPU DataFrame Library

cudf-alpha. [ARCHIVED] cuDF [alpha] - RAPIDS Merge of GoAi into cuDF

cuml. cuML - RAPIDS Machine Learning Library

Coursera-ML-AndrewNg-Notes. 吴恩达老师的机器学习课程个人笔记

CID. Kaggle Camera ID competition

kaggle-prudential. Python

instacart-basket-prediction. RNNs (and other stuff) for Kaggle's Instacart order prediction competition

darknet. Convolutional Neural Networks

dmn-tensorflow. Dynamic Memory Networks (https://arxiv.org/abs/1603.01417) in Tensorflow

fast_tffm. fast_tffm: Tensorflow-based Distributed Factorization Machine

kaggle-HomeDepot. 3rd Place Solution for HomeDepot Product Search Results Relevance Competition on Kaggle.

genentech-insight. Jupyter Notebook

kaggle_Microsoft_Malware. code for kaggle competition Microsoft malware classification