OrenLeung
@teslamotors @uWaterloo | Former @nvidia @Cohere-AI @uptake @hackclub @Voic.AI
@uWaterlooToronto, Canada
Pinned Repositories
flash-attention
Fast and memory-efficient exact attention
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
cutlass
CUDA Templates for Linear Algebra Subroutines
nccl
Optimized primitives for collective multi-GPU communication
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
streaming
A Data Streaming Library for Efficient Neural Network Training
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
OrenLeung's Repositories
OrenLeung/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
OrenLeung/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
OrenLeung/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
OrenLeung/streaming
A Data Streaming Library for Efficient Neural Network Training