「随笔小记」大模型随笔
「实习笔记」Paddle组合机制设计与开发
「论文笔记」PiPAD: Pipelined and Parallel Dynamic GNN Training on GPUs
「论文笔记」Ekko: A Large-Scale Deep Learning Recommender System with Low-Latency Model Update
「论文笔记」DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference
「论文笔记」Fleche: An Efficient GPU Embedding Cache for Personalized Recommendations
「论文笔记」JiZhi: A Fast and Cost-Eective Model-As-A-Service System for Web-Scale Online Inference at Baidu
「论文笔记」PetPS: Supporting Huge Embedding Models with Persistent Memory
「论文笔记」Hercules: Heterogeneity-Aware Inference Serving for At-Scale Personalized Recommendation
「论文笔记」Single-shot Embedding Dimension Search in Recommender System
avatar
zerorains
No matter what happens, I will do my best.
Follow Me
公告
主业想做大模型推理,目前也正在努力学习中。副业做数据库中执行传统模型的推理优化。