mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-11-04 09:32:00 +00:00 
			
		
		
		
	server : purge slots one by one
This commit is contained in:
		@@ -2725,6 +2725,9 @@ struct server_context {
 | 
			
		||||
                slot.prompt.tokens.clear();
 | 
			
		||||
 | 
			
		||||
                res = true;
 | 
			
		||||
 | 
			
		||||
                // purge slots one by one
 | 
			
		||||
                break;
 | 
			
		||||
            }
 | 
			
		||||
        }
 | 
			
		||||
 | 
			
		||||
 
 | 
			
		||||
		Reference in New Issue
	
	Block a user