Pinned Repositories
bmmaudio
Audio Analyzer for vup
cuda-samples-cn
cuda samples chinese
dnn-cookbook
Network Interpretation, include deploy
llm-deploy
AI Infra LLM infer/ tensorrt-llm/ vllm
pytorch-quantization
QAT
tensorrt-insight
deep insight tensorrt
trt-samples-for-hackathon-cn
中文版本
xinfer
infer engine
FasterTransformer
Transformer related optimization, including BERT, GPT
TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
lix19937's Repositories
lix19937/llm-deploy
AI Infra LLM infer/ tensorrt-llm/ vllm
lix19937/dnn-cookbook
Network Interpretation, include deploy
lix19937/xinfer
infer engine
lix19937/bmmaudio
Audio Analyzer for vup
lix19937/trt-samples-for-hackathon-cn
中文版本
lix19937/cuda-samples-cn
cuda samples chinese
lix19937/pytorch-quantization
QAT
lix19937/tensorrt-insight
deep insight tensorrt
lix19937/auto_download
auto download html
lix19937/cuda-c-best-practices-guide-chinese
nv cuda-c-best-practices-guide 中文版
lix19937/triton
make triton as infer framework
lix19937/cmake-examples
Useful CMake Examples
lix19937/CodeFormer
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
lix19937/cuda-programming-guide-chinese
lix19937/cv-cookbook
image process
lix19937/emojicpp
Emoji :smile: for c++ developers :+1:
lix19937/FasterTransformer
Transformer related optimization, including BERT, GPT
lix19937/FasterTransformer-detr3d
lix19937/gpustat
📊 A simple command-line utility for querying and monitoring GPU status
lix19937/I-S00N
lix19937/leetcode
lix19937/Lidar_AI_Solution
A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).
lix19937/lix19937
main profile
lix19937/lix19937.github.io
Github Pages template for academic personal websites
lix19937/PdfPasswordRemover
We had a problem in our Hospital with supplier's invoices containing password or security restriction into the PDF. This tool helps us to make a copy of the PDF and removes the password so the document can be analyzed by our OCR.
lix19937/sewar
All image quality metrics you need in one package.
lix19937/snpe
高通平台部署
lix19937/TIM-VX
Verisilicon Tensor Interface Module
lix19937/ViT-pytorch
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
lix19937/yolo_quantization
Based of paper "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"