Wilber's repositories
jiweibo.github.io
Weibo's blog
onnx_bench
onnx benchmark and tools
iree
👻
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
onnx-mlir
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
Paddle
PArallel Distributed Deep LEarning (『飞桨』核心框架,高性能单机、分布式训练和跨平台部署)
Paddle-Lite
Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎)
triton
Development repository for the Triton language and compiler
tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
CINN
Compiler Infrastructure for Neural Networks
CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计
env
Software Development Environment
Halide
a language for fast, portable data-parallel computation
mlir-mma
Optimize gpu mma based on mlir.
MMA
Matrix Multiplication Addition
mobile-aloha
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
PaddleTest
PaddlePaddle TestSuite
ProjectTest
some project demo
Scripts
Commonly used scripts or simple and useful programs
StarInf
A useless trash.
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.
tf-serving
A flexible, high-performance serving system for machine learning models
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
triton_server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
WeChatMsg
提取微信聊天记录,将其导出成HTML、Word、CSV文档永久保存,对聊天记录进行分析生成年度聊天报告