mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-11-03 09:22:01 +00:00 
			
		
		
		
	This commit enables the `--no-warmup` option for the llama-embeddings. The motivation for this change is to allow the user to disable the warmup when running the the program.
		
			
				
	
	
	
		
			100 KiB
		
	
	
	
	
	
	
	
			
		
		
	
	
			100 KiB