[FAST'25] Mooncake: Trading More Storage for Less Computation — A KVCache-centric Architecture for Serving LLM Chatbot 论文阅读

非常好! 目前共计 200 篇日志。 继续努力。

202620

10-11

[FAST'25] Mooncake: Trading More Storage for Less Computation — A KVCache-centric Architecture for Serving LLM Chatbot 论文阅读

08-09

[SIGMOD'27] HierarchicalKV: A GPU Hash Table with Cache Semantics for Continuous Online Embedding Storage 阅读笔记

06-16

[CIKM'24] TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling 论文精读

06-16

[KDD'23] TWIN: TWo-stage Interest Network 论文精读

06-16

[CIKM'20] SIM: Search-based User Interest Modeling with Lifelong Sequential Behavior Data 论文精读

06-16

[AAAI'19] DIEN: Deep Interest Evolution Network for Click-Through Rate Prediction 论文精读

06-16

[KDD'18] DIN: Deep Interest Network for Click-Through Rate Prediction 论文精读

04-19

[SysML'18] Compiling Machine Learning Programs via High-Level Tracing (JAX) 论文阅读

03-30

[arXiv'25] TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate 论文阅读

03-29

[FAST'20] HotRing: A Hotspot-Aware In-Memory Key-Value Store 论文阅读

02-23

[arXiv'25] MTGRBoost: Boosting Large-scale Generative Recommendation Models in Meituan 论文阅读

02-22

[ICDE'22] PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems 论文阅读

02-08

[NeurIPS'12] Large Scale Distributed Deep Networks (DistBelief) 阅读笔记

02-07

[MAPL@PLDI'19] Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations 阅读笔记

02-01

[OSDI'18] TVM: An Automated End-to-End Optimizing Compiler for Deep Learning 阅读笔记

01-13

[VLDB'21] Constructing and Analyzing the LSM Compaction Design Space 论文阅读

01-12

Slub 分配器 -- Linux 内核对 Slab 的优化

01-11

[ICDE'13] The Adaptive Radix Tree: ARTful Indexing for Main-Memory Databases 论文阅读

01-11

[USTC'94] The Slab Allocator: An Object-Caching Kernel Memory Allocator 论文阅读

01-11

内存管理串讲