ML System
60
QLoRA: Efficient Finetuning of Quantized LLMs
LoRA: Low-Rank Adaptation of Large Language Models
SGLang: Efficient Execution of Structured Language Model Programs
PagedAttention: Efficient Memory Management for Large Language Model Serving with PagedAttention
ORCA: A Distributed Serving System for Transformer-Based Generative Models
OnlineSoftmax: Online normalizer calculation for softmax
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
LLM Systems 24: Efficient LLM Inference with PagedAttention and vLLM
LLM Systems 23: Design of Efficient LLM Inference Server
LLM Systems 22: Flash Attention: Optimizing Attention for Modern Hardware
More...
数据库
16
读论文
6
DB 论文阅读:2005~2024 近 20 年数据库领域回顾
DB 论文阅读:关系型数据库在 ANNS 上为什么慢?
DB 论文阅读:Product Quantization for Nearest Neighbor Search
DB 论文阅读:Hierarchical Navigable Small World
DB 论文阅读:Approximate nearest neighbor algorithm based on navigable small world graphs
DB 论文阅读:A Relational Model of Data for Large Shared Data Banks