Summary: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
论文速览 ‘FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness’
Summary: DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
论文速览 ‘DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving’
Summary: Fast Inference from Transformers via Speculative Decoding
论文速览：‘Fast Inference from Transformers via Speculative Decoding’
Summary: MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
论文速览：‘MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation’
Summary: Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing
论文速览：‘Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing’
Summary: Efficient Memory Management for Large Language Model Serving with PagedAttention
论文速览：‘Efficient Memory Management for Large Language Model Serving with PagedAttention’
Summary: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
论文速览： ‘Incentivizing Reasoning Capability in LLMs via Reinforcement Learning’
TVM: 2D Depth Conv GPU Optimization
这篇博客展示了使用TVM在GPU上进行2D深度卷积的优化技术，包括块和线程组织、内存层次结构利用和维度融合等。
TVM: GEMM GPU Optimization
本博客展示了使用 TVM 在 GPU 上优化 GEMM（通用矩阵乘法）的技术，包括线程组织和内存层次结构利用
TVM: 1D convolution GPU Optimization
这篇博客展示了使用TVM对1D GPU卷积的优化技术，包括线程组织、内存层次结构利用和低级优化。