mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-28 08:31:25 +00:00 
			
		
		
		
	 f486f6e1e5
			
		
	
	f486f6e1e5
	
	
	
		
			
			* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverted Makefile * Fixed include * Removed sched.h from ggml.h, moved ggml_get_numa_affinity into ggml.c, removed trailing whitespace and fixed up a few inconsistent variables * removed trailing whitespace * Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverting Makefile * Fixed a number of issues with the move from BOOL to ggml_numa_strategies. Added a note about mirror mode note being implemented yet * Removing MIRROR_MODE code for this PR * Removing last bit of MIRROR_MODE code for this PR * Removing unneeded branch in server.cpp example and moving get_numa_affinity and making it static * Fixed lingering init_llama_backend() bool calls in tests and examples * Remote enum llama_numa_strategies * Revert bad merge with dynatemp flags * add missing enum ggml_numa_strategies declaration and revert sync problem with master * add missing enum ggml_numa_strategies declaration * fixed ggml_init_numa variable * Update ggml.h Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update READMEs with info about numa flags, change INTERLEAVE strategy name to DISTRIBUTE everywhere, implement the improved distribution strategy from @rankaiyx, fix a spelling mistake and un-merge some bad merges * split numa init out from llama_backend_init and created llama_numa_init. Updated all code paths and samples * Fix up some boolean vs enum comparisons * Added #ifdefs for non-Linux OS that don't have cpu_set_t datatype * Update ggml.h Align enum values Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c Remove whitespace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c align paremeters Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/server/server.cpp remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update common/common.cpp Remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * unified ggml_numa_strategy enum and fixed text alignment in server.cpp example * Update ggml.c simplified return for platforms without NUMA support Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * removed redundant else from cli argument processing of --numa * whitespace --------- Co-authored-by: root <root@nenya.lothlorien.ca> Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Jared Van Bortel <jared@nomic.ai>
		
			
				
	
	
		
			28 lines
		
	
	
		
			763 B
		
	
	
	
		
			C++
		
	
	
	
	
	
			
		
		
	
	
			28 lines
		
	
	
		
			763 B
		
	
	
	
		
			C++
		
	
	
	
	
	
| #include "llama.h"
 | |
| #include "get-model.h"
 | |
| 
 | |
| #include <cstdlib>
 | |
| 
 | |
| int main(int argc, char *argv[] ) {
 | |
|     auto * model_path = get_model_or_exit(argc, argv);
 | |
|     auto * file = fopen(model_path, "r");
 | |
|     if (file == nullptr) {
 | |
|         fprintf(stderr, "no model at '%s' found\n", model_path);
 | |
|         return EXIT_FAILURE;
 | |
|     }
 | |
| 
 | |
|     fprintf(stderr, "using '%s'\n", model_path);
 | |
|     fclose(file);
 | |
| 
 | |
|     llama_backend_init();
 | |
|     auto params = llama_model_params{};
 | |
|     params.use_mmap = false;
 | |
|     params.progress_callback = [](float progress, void * ctx){
 | |
|         (void) ctx;
 | |
|         return progress > 0.50;
 | |
|     };
 | |
|     auto * model = llama_load_model_from_file(model_path, params);
 | |
|     llama_backend_free();
 | |
|     return model == nullptr ? EXIT_SUCCESS : EXIT_FAILURE;
 | |
| }
 |