T800GHB

HanBing Guo's starred repositories

tpu-mlir

Machine learning compiler based on MLIR for Sophgo TPU.

Language:C++NOASSERTION49500

llama2.c

Inference Llama 2 in one file of pure C

Language:CMIT1654200

Cpp-Templates-2ed

C++11/14/17/20 templates and generic programming, the most complex and difficult technical details of C++, indispensable in building infrastructure libraries.

Language:C++Apache-2.0158700

iree

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Language:C++Apache-2.0244600

mlir-tutorial

MLIR For Beginners tutorial

Language:C++60500

trtllm-llama

☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化

Language:C++Apache-2.03500

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.

Language:C++Apache-2.0708300

ComputerArchitectureAndCppBooks

📚 计算机体系结构与C++书籍收集(持续更新)

MIT24800

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Language:C++Apache-2.0933300

byteir

A model compilation solution for various hardware

Language:MLIRApache-2.032000

folly

An open-source C++ library developed and used at Facebook.

Language:C++Apache-2.02730000

code_generator

Simple and straightforward code generator for creating program code. At the moment offers support for C++, Java and HTML5 for generating reports.

Language:PythonMIT9700

tvm_mlir_learn

compiler learning resources collect.

Language:Python187100

trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

Language:PythonApache-2.0138900

yoloair

🔥🔥🔥 专注于YOLOv5，YOLOv7、YOLOv8、YOLOv9改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

Language:PythonGPL-3.0238800

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Language:PythonApache-2.0447200