Lei Mao's Log Book
Lei Mao's Log BookCurriculumBlogArticlesProjectsPublicationsReadingsLifeEssayArchivesCategoriesTagsFAQs
  • Tags
  • Transformer

Grouped Query Attention Performance Theoretical Analysis

 02-03-2025 03-02-2025 blog 11 minutes read (About 1612 words)
Sharing Key and Value Tensors for a Group of Query Tensors to Mitigate Transformer Attention Layer Performance Bottleneck

 
Deep Learning, 
Neural Network, 
Transformer, 
Computer Architecture, 
Performance Optimization, 
Large Language Model  
  Read More

Transformer Vanilla Attention Performance Theoretical Analysis

 01-27-2025 03-02-2025 blog 9 minutes read (About 1275 words)
Performance Bottleneck for Serving Transformer Models

 
Deep Learning, 
Neural Network, 
Transformer, 
Computer Architecture, 
Performance Optimization, 
Large Language Model  
  Read More

Deformable Attention

 12-16-2023 12-16-2023 blog 34 minutes read (About 5063 words)
Attention with Learned Spatial Feature Sampling

 
Deep Learning, 
Computer Vision, 
Transformer, 
Attention  
  Read More

OpenAI GPT Models

 04-15-2023 04-15-2023 article 28 minutes read (About 4168 words)
Generative Pre-Trained Transformer Models From OpenAI

 
Deep Learning, 
Natural Language Processing, 
Transformer, 
Reinforcement Learning, 
OpenAI, 
GPT, 
ChatGPT, 
InstructGPT  
  Read More

Transformer Autoregressive Inference Optimization

 04-06-2023 04-06-2023 article 27 minutes read (About 4084 words)
Principles for Faster Transformer Inference

 
Deep Learning, 
Inference, 
Natural Language Processing, 
Optimization, 
Transformer, 
Accelerated Computing  
  Read More

PyTorch Dynamic Quantization

 11-14-2020 04-29-2021 blog 8 minutes read (About 1193 words)
PyTorch Dynamic Quantization for Transformers

 
Quantization, 
Transformer, 
PyTorch, 
HuggingFace  
  Read More

Evolved Transformer Explained

 03-07-2020 03-07-2020 blog 5 minutes read (About 777 words)
Evolution Search on Transformer Neural Network Architectures

 
Machine Learning, 
Deep Learning, 
Natural Language Processing, 
Transformer, 
Neural Architecture Search, 
Evolution Algorithm  
  Read More

Transformer Explained In One Single Page

 06-01-2019 02-09-2023 blog 23 minutes read (About 3454 words)
Attention is All You Need Mathematically

 
Deep Learning, 
Natural Language Processing, 
Transformer, 
Machine Translation  
  Read More
Lei Mao

Lei Mao

Artificial Intelligence Machine Learning Computer Science

Santa Clara, California

Posts

1056

Categories

7

Tags

687

  Follow   Sponsor

Advertisement


Categories

  • article20
  • blog508
  • essay269
  • life229
  • miscellaneous2
  • project20
  • reading8

follow.it

Recents

05-08-2025

Tensor Calculus Layout Conventions

blog

05-07-2025

幸运钥匙

essay

05-04-2025

人在湾区五月份长冻疮

essay

05-03-2025

ICML 2025 Area Chair Experience

blog

05-03-2025

Sunol Wilderness Regional Preserve 徒步

life

Archives

  • May 20255
  • April 202521
  • March 202525
  • February 202521
  • January 202523
  • See All >>

Tags

Outdoors232
Hiking177
California164
CPP108
Mathematics89
Deep Learning78
CUDA50
Running46
Software Engineering35
Machine Learning34
Python32
Statistics31
Park30
Linux29
Racing29
Docker26
Movie25
China23
Physics23
Museum22
See All >>
Lei Mao's Log Book

© 2017-2025 Lei Mao  Powered by Hexo & Icarus
Site UV:  Site PV:

×