8000 antmikinka (Anthony Mikinka) · GitHub
[go: up one dir, main page]
Skip to content
8000
View antmikinka's full-sized avatar
🎯
Focusing
🎯
Focusing
44 followers · 131 following

Achievements

Achievement: Pair Extraordinairex3Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Highlights

  • Pro

Block or report antmikinka

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
antmikinka/README.md

header

GitHub followers Profile Views

About Me

Building local-first AI and agent systems

Open source developer passionate about making AI accessible to everyone.

  • 🎓 B.S. Data Science @ Arizona State University (expected May 2027)
  • 💼 Ex AMD - Agentic AI R&D Intern (Jan–Aug 2026)
  • 🚀 Built Lemonade Interviewer for AMD's Lemonade SDK — open-source local AI platform for running LLMs, image generation & speech on your own GPU/NPU
  • 🤝 Open source AI, edge inference, and agent orchestration

Publications

arXiv: Universal Conditional Logic

GitHub Stats

GitHub Stats

Top Languages

GitHub Streak

Tech Stack

C++ TypeScript Python AMD

Connect

Hugging Face LinkedIn

🚀 Building Local AI for Everyone.

Pinned Loading

  1. Optimization Guidelines for the Appl... Optimization Guidelines for the Apple Neural Engine (ANE)
    1 
    Comprehensive Optimization Guidelines for the Apple Neural Engine (ANE)
    2 
    Tensor Considerations:
    3 
    
              
    
              
    
                4
                
    Shapes: Utilize tensor shapes that are powers of 2 (e.g., 2, 4, 8, 16) to enhance memory allocation and access.
    
              
    
              
    
                5
                
    Sizes: Keep tensor sizes small, aiming for multiples of 16 (e.g., 16, 32, 48, 64) to optimize memory usage.
    
              
    
          
    
    
    
  
    

    2. 

      
  2. 
  
    
    
    
      
    
        
    
            
          AppleNeuralEngine-Kit  AppleNeuralEngine-Kit          Public
        
    
      
    


      
    
        (WIP) LLM Optimization for Apple Neural Engine
      
    

      
    
          
  
  Swift


          
            
    

            6
          
          
            
    

            1
          
      
    
    
    
  
    

    3. 

      
  3. 
  
    
    
    
      
    
        
    
            
          AI-Context-Document  AI-Context-Document          Public
        
    
      
    


      
    
        
      
    

      
    
          
            
    

            3
          
      
    
    
    
  
    

    4. 

      
  4. 
  
    
    
    
      
    
        
    
            
          bmad-code-org/BMAD-METHOD  bmad-code-org/BMAD-METHOD          Public
        
    
      
    


      
    
        Breakthrough Method for Agile Ai Driven Development
      
    

      
    
          
  
  Python


          
            
    

            55.1k
          
          
            
    

            6.1k
          
      
    
    
    
  
    

    5. 

      
  5. 
  
    
    
    
      
    
        
    
            
          Universal-Conditional-Logic  Universal-Conditional-Logic          Public
        
    
      
    


      
    
        Universal Conditional Logic (UCL): prompt-optimization research and the UCL Prompt Builder.
      
    

      
    
          
  
  Python


          
            
    

            4
          
      
    
    
    
  
    

    6. 

      
  6. 
  
    
    
    
      
    
        
    
            
          ccmg  ccmg          Public
        
    
      
    


      
    
        a teaser of what may be coming ;)
      
    

      
    
          
  
  Python


          
            
    

            4
          
      
    
    
    
  
    

    7. 












      
  
        

          
  
    
    

        

        

  





        

      





      

  


          



    




  

    

    

    





    

    

    

  


0