WebDOI: 10.1145/3437984.3458838 Corpus ID: 232168739; DISC: A Dynamic Shape Compiler for Machine Learning Workloads @article{Zhu2024DISCAD, title={DISC: A Dynamic Shape Compiler for Machine Learning Workloads}, author={Kai Zhu and Wenyi Zhao and Zhen Zheng and Tianyou Guo and Pengzhan Zhao and Junjie Bai and Jun … WebMar 14, 2024 · 欢迎走进走进阿里云机器学习PAI AICompiler编译器系列。近期,阿里云机器学习PAI团队全新上线一套Dynamic Shape Compiler框架,不仅作为AICompiler技术栈中原有的Static Shape Compiler框架的重要补充,更是增加了Compiler在企业级数据处理应用的无限可能,在提升数据处理效率的同时,大幅提升AI工程化效率。
BladeDISC/pass_pipeline.md at main · alibaba/BladeDISC
Web3 rows · for dynamic shape workloads, named DISC . DISC enriches a set of IR to form a fully ... WebMar 9, 2024 · It addresses the kernel fusion problem of dynamic shapes with shape propagation and constraints collecting methods. This is the first work to demonstrate how … kindnesh thai restaurant
DISC: A Dynamic Shape Compiler for Machine Learning Workloads
WebDISC: A dynamic shape compiler for machine learning workloads. K Zhu, WY Zhao, Z Zheng, TY Guo, PZ Zhao, JJ Bai, J Yang, XY Liu, ... Proceedings of the 1st Workshop on Machine Learning and Systems, 89-95, 2024. 8: 2024: Parameter-Efficient Sparsity for Large Language Models Fine-Tuning. WebMar 31, 2024 · 本文主要介绍这套动态shape编译框架,对更多技术细节兴趣的读者可以参考DISC: A Dynamic Shape Compiler for Machine Learning Workloads. 从PAI团队三年前 … WebMar 29, 2024 · TensorFlow-TensorRT (TF-TRT) is a deep-learning compiler for TensorFlow that optimizes TF models for inference on NVIDIA devices. TF-TRT is the TensorFlow integration for NVIDIA’s TensorRT (TRT) High-Performance Deep-Learning Inference SDK, allowing users to take advantage of its functionality directly within the TensorFlow … kindness and compassion in nursing