BladeDISC深度学习编译器
BladeDISC 是阿里巴巴集团自主研发并开源的深度学习编译器,旨在为用户提供通用、透明、易用的深度学习性能优化能力。BladeDISC支持主流的机器学习框架,如TensorFlow、PyTorch,支持主流硬件,如GPGPU、CPU 等。BladeDISC在架构层面根本地解决了深度学习领域具有动态尺寸Tensor的优化难题,大大提升了深度学习模型的性能,降低了部署的难度。同时,BladeDISC 还提供了多种灵活的部署方案,包括插件模式集成到Pytorch和TensorFlow运行时,也包括独立运行与AOT编译的支持。BladeDISC源于阿里巴巴内部诸多的深度学习加速场景,也同时服务于阿里云上的客户,在生产中经受了广泛的考验。
功能与支持
前端框架支持情况
TensorFlow | PyTorch | |
---|---|---|
推理 | Yes | Yes |
训练 | Yes | Ongoing |
后端硬件支持情况
Status | |
---|---|
Nvidia GPU | Yes |
AMD GPU | Yes |
Hygon DCU | Yes |
X86 | Yes |
AArch64 | Yes |
典型模型的加速效果
入门与示例
- How to Setup and Build from Source
- Use Case of TensorFlow Inference and Training
- Use Case of PyTorch Inference
论文发表
开发入门
- Tutorial: A Walkthough of the BladeDISC Pass Pipeline
- Introduction on Runtime Abstraction Layer
- TorchBlade Overview
- Tutorial: How to Add a New Torch Operator Converter
演讲与文章
- DISC: A Dynamic Shape Compiler for Machine Learning Workload
- Performance optimization practice for dynamic shape AI workloads via a compiler-based approach
- 2022/07/31 BladeDISC: A Practice of Dynamic Shape Deep Learning Compiler(Chinese)
- 2022/07/07 BladeDISC and Torch-MLIR Roadmap Talk on Torch-MLIR Community
- GTC22-S41073, Generalized and Transparent AI Optimization Solutions with AI Compilers from Cloud Service
- GTC22-S41395, Easier-to-use and More Robust TensorRT via PAI-Blade
评论