Blog

1. How GPUs Talk to Each Other

   2026-10-14

   • LLM
   • inference
   • tensor parallelism
   • NCCL

2. PagedAttention, Visualized

   2026-10-05

   • LLM
   • inference
   • vLLM
   • KV cache

3. Big Debt Crisis Analysis

   2020-04-20

   • random

4. Convolution is Matrix Multiplication

   2019-11-18

   • neural network
   • deep learning
   • parallelism
   • convolution

5. Parallel Deep Learning

   2019-10-20

   • neural network
   • deep learning
   • parallelism
   • GPU

6. When to use GPU for training?

   2019-09-04

   • PyTorch
   • CUDA
   • GPU

7. PyTorch Autograd Computation Graph

   2019-08-30

   • PyTorch
   • deep learning
   • neural networks

8. Tiled Matrix Multiplication

   2019-08-24

   • deep learning
   • matrix multiplication
   • CUDA
   • GPU

9. Mathematical Morphology Visualized

   2019-08-14

   • computer vision
   • image analysis

10. Finding eigenvalues proof explained

    2019-07-26

    • eigenvector
    • eigenvalue

11. Generalized Hough Transform

    2019-07-01

    • Hough Transform
    • computer vision
    • image analysis

12. Linear to Fully Convolutional Networks

    2019-06-19

    • deep learning
    • convolution
    • neural networks

13. Matrix Multiplication is Parallel

    2019-06-17

    • deep learning
    • matrix multiplication
    • parallelism

14. Probabilistic Classifier

    2019-06-12

    • machine learning
    • image analysis
    • classification
    • probability

15. Image Restoration

    2019-06-10

    • image analysis
    • restoration filter

16. Do you even know cross entropy?

    2019-06-01

    • cross entropy
    • entropy
    • machine learning