mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-31 08:51:55 +00:00 
			
		
		
		
	
		
			
				
	
	
		
			12 lines
		
	
	
		
			332 B
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			12 lines
		
	
	
		
			332 B
		
	
	
	
		
			C
		
	
	
	
	
	
| #ifdef  __cplusplus
 | |
| extern "C" {
 | |
| #endif
 | |
| 
 | |
| void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
 | |
| void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
 | |
| void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream);
 | |
| 
 | |
| #ifdef  __cplusplus
 | |
| }
 | |
| #endif
 | 
