jsonlee0x02 Goto Github PK

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

cuda_deconvolution

Multi-threaded GPU (CUDA) based implementation of the Högbom CLEAN deconvolution algorithm

cutlass

CUDA Templates for Linear Algebra Subroutines

hipify

HIPIFY: Convert CUDA to Portable C++ Code

info

ir2vec

Implementation of IR2Vec, published in ACM TACO

jsonlee0x02

llvm-techniques-tips-and-best-practices-clang-and-middle-end-libraries

LLVM Techniques, Tips, and Best Practices Clang and Middle-End Libraries, published by Packt

mlu-ops

Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .

nn_dataflow

Explore the energy-efficient dataflow scheduling for neural networks.

rvv_example

Simple demonstration of using the RISC-V Vector extension

stablehlo

Backward compatible ML compute opset inspired by HLO/MHLO

tpp-mlir

TPP experimentation on MLIR for linear algebra

treebeard

An optimizing compiler for decision tree ensemble inference.

triton

Development repository for the Triton language and compiler

triton-cpu

An experimental CPU backend for Triton (https//github.com/openai/triton)

triton-shared

Shared Middle-Layer for Triton Compilation

visionbevdetectionsurvey

BEV基本原理说明：https://www.cnblogs.com/wujianming-110117/p/17207533.html