Paper_summary - Category - Wentao's Blog

Paper_summary

2025

Summary: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning 05-28

Summary: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness 05-22

Summary: DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving 05-17

Summary: Fast Inference from Transformers via Speculative Decoding 05-11

Summary: MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation 04-29

Summary: Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing 04-27

Summary: Efficient Memory Management for Large Language Model Serving with PagedAttention 04-17

Summary: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 04-13

Summary: ZeRO: Memory Optimizations Toward Training Trillion Parameter Models 04-02

Summary: Communication-Efficient Learning of Deep Networks from Decentralized Data 03-25

1
2