sophgo / tpu-mlirLinks
Machine learning compiler based on MLIR for Sophgo TPU.
☆798Updated last week
Alternatives and similar repositories for tpu-mlir
Users that are interested in tpu-mlir are comparing it to the libraries listed below
Sorting:
- An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).☆636Updated last week
- MegCC是一个运行时超轻量,高效,移植简单的深度学习模型编译器☆486Updated 11 months ago
- Hands-On Practical MLIR Tutorial☆613Updated last year
- how to learn PyTorch and OneFlow☆456Updated last year
- compiler learning resources collect.☆2,539Updated 6 months ago
- A Workflow-based Multi-platform AI Inference and Deployment Framework | 一款基于工作流的多端AI推理部署框架☆1,211Updated this week
- Development repository for the Triton-Linalg conversion☆202Updated 8 months ago
- row-major matmul optimization☆674Updated last month
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,755Updated last year
- Run generative AI models in sophgo BM1684X/BM1688☆248Updated last week
- 先进编译实验室的个人主页☆147Updated 5 months ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆896Updated 9 months ago
- A primitive library for neural network☆1,360Updated 10 months ago
- A model compilation solution for various hardware☆450Updated last month
- PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)☆96Updated this week
- A CUDA tutorial to make people learn CUDA program from 0☆251Updated last year
- CUDA 算子手撕与面试指南☆621Updated last month
- Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .☆134Updated last week
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆921Updated last week
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆511Updated 11 months ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆480Updated last year
- A simple high performance CUDA GEMM implementation.☆409Updated last year
- A CPU tool for benchmarking the peak of floating points☆561Updated 2 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆690Updated last week
- code reading for tvm☆76Updated 3 years ago
- learning how CUDA works☆323Updated 7 months ago
- Hands-On Practical MLIR Tutorial☆32Updated last month
- ☆297Updated 11 months ago
- ☆297Updated 3 years ago
- Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.☆384Updated 9 months ago