Summary: Efficient Memory Management for Large Language Model Serving with PagedAttention
Summary for paper ‘Efficient Memory Management for Large Language Model Serving with PagedAttention’
Summary: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Summary for paper ‘Incentivizing Reasoning Capability in LLMs via Reinforcement Learning’
TVM: 2D Depth Conv GPU Optimization
This blog demonstrates optimization techniques for 2D depth Convolution in GPU using TVM, including block and thread organization, memory hierarchy exploitation and dimension fuse, etc.
TVM: GEMM GPU Optimization
This blog demonstrates optimization techniques for GEMM in GPU using TVM, including thread organization and memory hierarchy exploitation.
TVM: 1D convolution GPU Optimization
This blog demonstrates optimization techniques for 1D GPU convolution using TVM, including thread organization, memory hierarchy exploitation, and low-level optimizations.
Summary: ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
Summary for paper ‘ZeRO: Memory Optimizations Toward Training Trillion Parameter Models’
TVM: 1D convolution CPU Optimization
This blog demonstrates optimization techniques for 1D convolution using TVM, including parallelization, loop tiling, vectorization, and unrolling.
Summary: Communication-Efficient Learning of Deep Networks from Decentralized Data
Summary for paper ‘Communication-Efficient Learning of Deep Networks from Decentralized Data’
2025 Technical Notes(2)
Technical notes during 2025.
Summary: Large Scale Distributed Deep Networks
Summary for paper ‘Large Scale Distributed Deep Networks’