mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-29 08:41:22 +00:00 
			
		
		
		
	 436e561931
			
		
	
	436e561931
	
	
	
		
			
			* Be more strict about converting float to double * Test equivalence of round, SILU implementations Test module is commented out in CMakeLists.txt because the tests may take a long time, depending on how much the compiler optimizes. * Fix softmax in perplexity.cpp * all : prefer float over double where appropriate * perplexity : add <cmath> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
		
			
				
	
	
		
			59 lines
		
	
	
		
			1.5 KiB
		
	
	
	
		
			C++
		
	
	
	
	
	
			
		
		
	
	
			59 lines
		
	
	
		
			1.5 KiB
		
	
	
	
		
			C++
		
	
	
	
	
	
| #include "ggml.h"
 | |
| #include "llama.h"
 | |
| 
 | |
| #include <cstdio>
 | |
| #include <string>
 | |
| 
 | |
| // usage:
 | |
| //  ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
 | |
| //
 | |
| int main(int argc, char ** argv) {
 | |
|     ggml_time_init();
 | |
| 
 | |
|     if (argc != 4) {
 | |
|         fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
 | |
|         fprintf(stderr, "  type = 2 - q4_0\n");
 | |
|         fprintf(stderr, "  type = 3 - q4_1\n");
 | |
|         return 1;
 | |
|     }
 | |
| 
 | |
|     // needed to initialize f16 tables
 | |
|     {
 | |
|         struct ggml_init_params params = { 0, NULL };
 | |
|         struct ggml_context * ctx = ggml_init(params);
 | |
|         ggml_free(ctx);
 | |
|     }
 | |
| 
 | |
|     const std::string fname_inp = argv[1];
 | |
|     const std::string fname_out = argv[2];
 | |
| 
 | |
|     const int itype = atoi(argv[3]);
 | |
| 
 | |
|     const int64_t t_main_start_us = ggml_time_us();
 | |
| 
 | |
|     int64_t t_quantize_us = 0;
 | |
| 
 | |
|     // load the model
 | |
|     {
 | |
|         const int64_t t_start_us = ggml_time_us();
 | |
| 
 | |
|         if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype)) {
 | |
|             fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
 | |
|             return 1;
 | |
|         }
 | |
| 
 | |
|         t_quantize_us = ggml_time_us() - t_start_us;
 | |
|     }
 | |
| 
 | |
|     // report timing
 | |
|     {
 | |
|         const int64_t t_main_end_us = ggml_time_us();
 | |
| 
 | |
|         printf("\n");
 | |
|         printf("%s: quantize time = %8.2f ms\n", __func__, t_quantize_us/1000.0);
 | |
|         printf("%s:    total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0);
 | |
|     }
 | |
| 
 | |
|     return 0;
 | |
| }
 |