tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into xsn/private_batch_api

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 15:55:18 +01:00
parent 46596caf6d be7c303410
commit 17f954c8e2
173 changed files with 26425 additions and 16117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/cvector-generator/cvector-generator.cpp
View File

@ -342,7 +342,7 @@ static bool cb_eval(struct ggml_tensor * t, bool ask, void * user_data) {
}
static bool get_hidden_layers(llama_context * ctx, std::vector<llama_token> & tokens) {
llama_kv_cache_clear(ctx);
llama_kv_self_clear(ctx);
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0));
if (llama_decode_ext(ctx, batch.get())) {
fprintf(stderr, "%s : failed to eval\n", __func__);
@ -395,6 +395,8 @@ static int prepare_entries(common_params & params, train_context & ctx_train) {
int main(int argc, char ** argv) {
common_params params;
params.out_file = "control_vector.gguf";
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_CVECTOR_GENERATOR, print_usage)) {
return 1;
}
@ -499,7 +501,7 @@ int main(int argc, char ** argv) {
}
// write output vectors to gguf
export_gguf(ctx_train.v_final, params.cvector_outfile, model_hint);
export_gguf(ctx_train.v_final, params.out_file, model_hint);
llama_backend_free();