bytedance / matxscript
A high-performance, extensible Python AOT compiler.
☆413Updated last year
Related projects ⓘ
Alternatives and complementary repositories for matxscript
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆816Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆457Updated 8 months ago
- A high-performance framework for training wide-and-deep recommender systems on heterogeneous cluster☆157Updated 7 months ago
- deepx_core是一个专注于张量计算/深度学习的基础库☆370Updated last year
- A model compilation solution for various hardware☆378Updated last week
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆90Updated last year
- HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of…☆133Updated 2 months ago
- DeepLearning Framework Performance Profiling Toolkit☆277Updated 2 years ago
- 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☆473Updated 3 weeks ago
- Compiler Infrastructure for Neural Networks☆143Updated last year
- ☆289Updated this week
- A library for high performance deep learning inference on NVIDIA GPUs.☆547Updated 2 years ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆545Updated last month
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆263Updated last year
- tensorflow源码阅读笔记☆189Updated 6 years ago
- Bagua Speeds up PyTorch☆876Updated 3 months ago
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆390Updated this week
- TensorRT Plugin Autogen Tool☆367Updated last year
- ☆209Updated last year
- Running BERT without Padding☆460Updated 2 years ago
- ☆589Updated 5 months ago
- ☆123Updated 3 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆962Updated 2 months ago
- GLake: optimizing GPU memory management and IO transmission.☆379Updated 3 months ago
- row-major matmul optimization☆591Updated last year
- Universal cross-platform tokenizers binding to HF and sentencepiece☆274Updated this week
- The road to hack SysML and become an system expert☆437Updated last month
- Puck is a high-performance ANN search engine☆342Updated 5 months ago
- oneflow documentation☆68Updated 4 months ago
- embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等☆299Updated 5 months ago