Jackch-NV

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

cutlass

CUDA Templates for Linear Algebra Subroutines

FasterTransformer

Transformer related optimization, including BERT, GPT

smoothquant

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

TensorRT-LLM

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.

TRTLLM-w4afp8-fp8-mix-inference

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

FasterTransformer

Transformer related optimization, including BERT, GPT

Jackch-NV/TRTLLM-w4afp8-fp8-mix-inference

Jackch-NV/apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Jackch-NV/cutlass

CUDA Templates for Linear Algebra Subroutines

Jackch-NV/FasterTransformer

Transformer related optimization, including BERT, GPT

Jackch-NV/smoothquant

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Jackch-NV/Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Jackch-NV/TensorRT-LLM

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.