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

llama : add new llama_decode() API that works with llama_batch

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-18 14:23:52 +03:00
parent 58bb5110ca
commit 9f42e75489
13 changed files with 146 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/simple/simple.cpp
View File

@@ -76,7 +76,7 @@ int main(int argc, char ** argv) {
while (n_cur < n_gen) {
// evaluate the transformer
if (llama_eval(ctx, tokens_list.data(), int(tokens_list.size()), n_cur, params.n_threads)) {
if (llama_decode(ctx, llama_batch_get_one(tokens_list.data(), int(tokens_list.size()), n_cur, 0), params.n_threads)) {
fprintf(stderr, "%s : failed to eval\n", __func__);
return 1;
}