All Categories - Weile Luo's homepage

All Categories

Blog

Multimodal Agents: When LLMs Open Their Eyes to the World

DeepSeek NSA and DSA: From Native Sparse Attention to Fine-Grained Token Selection

Deep Research: How LLMs Evolve into Full-Stack AI Scientists

CUDA Micro-benchmarks in Practice (Part 2): Peak Compute, Memory Bandwidth, and Hopper Asynchronous Pipelines

CUDA Micro-benchmarks in Practice (Part 1): From Source and SASS to an Nsight Compute Evidence Chain

More >>

Paper Notes

PPoPP'21 | A Fast Work-Efficient SSSP Algorithm for GPUs

TACO'22 | Performance and Power Prediction for Concurrent Execution on GPUs

OSDI'20 | AntMan: Dynamic Scaling on GPU Clusters for Deep Learning

OSDI'18 | Gandiva: Introspective Cluster Scheduling for Deep Learning

RTSS'17 | GPU Scheduling on the NVIDIA TX2: Hidden Details Revealed

More >>