CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-09-14 16:08:52 -04:00
parent 4bb4b22a58 822b6322de
commit 63ac36b271
144 changed files with 11344 additions and 6693 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
examples/embedding/embedding.cpp
View File

@@ -1,3 +1,4 @@
#include "arg.h"
#include "common.h"
#include "llama.h"
@@ -79,8 +80,7 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
int main(int argc, char ** argv) {
gpt_params params;
if (!gpt_params_parse(argc, argv, params)) {
gpt_params_print_usage(argc, argv, params);
if (!gpt_params_parse(argc, argv, params, LLAMA_EXAMPLE_EMBEDDING)) {
return 1;
}
@@ -90,14 +90,6 @@ int main(int argc, char ** argv) {
print_build_info();
if (params.seed == LLAMA_DEFAULT_SEED) {
params.seed = time(NULL);
}
fprintf(stderr, "%s: seed = %u\n", __func__, params.seed);
std::mt19937 rng(params.seed);
llama_backend_init();
llama_numa_init(params.numa);
@@ -313,8 +305,10 @@ int main(int argc, char ** argv) {
if (notArray) fprintf(stdout, "\n}\n");
}
LOG_TEE("\n");
llama_perf_context_print(ctx);
// clean up
llama_print_timings(ctx);
llama_batch_free(batch);
llama_free(ctx);
llama_free_model(model);