This repository was archived by the owner on Sep 10, 2025. It is now read-only.
  
  
  - 
                Notifications
    You must be signed in to change notification settings 
- Fork 248
[distributed] prefill (single and multi-prompt) and single prompt generation and decoding #1133
          
     Merged
      
      
    Conversation
  
    
      This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
      Learn more about bidirectional Unicode characters
    
  
  
    
    | 🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1133
 Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 9242dfb with merge base 7a4f0d1 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. | 
              
                    kwen2501
  
              
              reviewed
              
                  
                    Sep 13, 2024 
                  
              
              
            
            
              
                    kwen2501
  
              
              reviewed
              
                  
                    Sep 13, 2024 
                  
              
              
            
            
… lessw2020/prefill
              
                    kwen2501
  
              
              approved these changes
              
                  
                    Sep 14, 2024 
                  
              
              
            
            
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank for the big effort. LGTM. Would appreciate it if the code can be cleaned up more (please see comments in line)
| Minor comment: | 
leaving as commented out as will reuse for multi-prompt work.
| Rebasing to pick up CI fix | 
  
      Sign up for free
      to subscribe to this conversation on GitHub.
      Already have an account?
      Sign in.
  
      
  Add this suggestion to a batch that can be applied as a single commit.
  This suggestion is invalid because no changes were made to the code.
  Suggestions cannot be applied while the pull request is closed.
  Suggestions cannot be applied while viewing a subset of changes.
  Only one suggestion per line can be applied in a batch.
  Add this suggestion to a batch that can be applied as a single commit.
  Applying suggestions on deleted lines is not supported.
  You must change the existing code in this line in order to create a valid suggestion.
  Outdated suggestions cannot be applied.
  This suggestion has been applied or marked resolved.
  Suggestions cannot be applied from pending reviews.
  Suggestions cannot be applied on multi-line comments.
  Suggestions cannot be applied while the pull request is queued to merge.
  Suggestion cannot be applied right now. Please check back later.
  
    
  
    
This PR:

1 - enables single or batch prompt prefill and decoding.
2 - adds three supporting functions for this (encode string, create padded prompt, batch decode next tokens).
Single:
Batch - prompts:

and batch decode:

3 - enables single prompt decoding up to max_tokens with formatted output: