OrenLeung

@teslamotors @uWaterloo | Former @nvidia @Cohere-AI @uptake @hackclub @Voic.AI

@uWaterlooToronto, Canada

Pinned Repositories

flash-attention
Fast and memory-efficient exact attention
Language:Python11.9k 103 8671.1k
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Language:Python18k 156 1.4k2k
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Language:Python34.6k 355 3025.3k
cutlass
CUDA Templates for Linear Algebra Subroutines
Language:C++4.8k 105 924836
nccl
Optimized primitives for collective multi-GPU communication
Language:C++3k 151 1.2k758
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
Language:Python00
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Language:Python00
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python00
streaming
A Data Streaming Library for Efficient Neural Network Training
Language:Python00
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python80.2k 1.7k 43.1k21.6k

OrenLeung's Repositories

OrenLeung/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
Language:Python00
OrenLeung/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Language:Python00
OrenLeung/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python00
OrenLeung/streaming
A Data Streaming Library for Efficient Neural Network Training
Language:Python00