mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-01 07:30:17 +01:00
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>
45 lines
1.2 KiB
C++
45 lines
1.2 KiB
C++
#include "common.h"
|
|
#include "llama.h"
|
|
|
|
#include <cmath>
|
|
#include <cstdio>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
int main(int argc, char ** argv) {
|
|
if (argc < 3 || argv[1][0] == '-') {
|
|
printf("usage: %s MODEL_PATH PROMPT [--ids]\n" , argv[0]);
|
|
return 1;
|
|
}
|
|
|
|
const char * model_path = argv[1];
|
|
const char * prompt = argv[2];
|
|
|
|
const bool printing_ids = argc > 3 && std::string(argv[3]) == "--ids";
|
|
|
|
llama_backend_init();
|
|
|
|
llama_model_params model_params = llama_model_default_params();
|
|
model_params.vocab_only = true;
|
|
llama_model * model = llama_load_model_from_file(model_path, model_params);
|
|
|
|
llama_context_params ctx_params = llama_context_default_params();
|
|
llama_context * ctx = llama_new_context_with_model(model, ctx_params);
|
|
|
|
const bool add_bos = llama_should_add_bos_token(model);
|
|
|
|
std::vector<llama_token> tokens;
|
|
|
|
tokens = ::llama_tokenize(model, prompt, add_bos, true);
|
|
|
|
for (int i = 0; i < (int) tokens.size(); i++) {
|
|
if (printing_ids) {
|
|
printf("%d\n", tokens[i]);
|
|
} else {
|
|
printf("%6d -> '%s'\n", tokens[i], llama_token_to_piece(ctx, tokens[i]).c_str());
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|