mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-11-04 09:32:00 +00:00 
			
		
		
		
	* speculative : update default params * speculative : do not discard the last drafted token
		
			
				
	
	
	
		
			9.1 KiB
		
	
	
	
	
	
	
	
			
		
		
	
	
			9.1 KiB