tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix llama_batch_ext_init_from_text

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 23:09:27 +01:00
parent 65f0184517
commit c3dd79007b
18 changed files with 40 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/cvector-generator/cvector-generator.cpp
View File

@ -343,7 +343,8 @@ 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_self_clear(ctx);
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0));
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0, true));
llama_batch_ext_set_output_last(batch.get());
if (llama_decode_ext(ctx, batch.get())) {
fprintf(stderr, "%s : failed to eval\n", __func__);
return false;