CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-20 12:07:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : unified KV cache + batch inference API

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-18 10:08:22 +03:00
parent fad56936d4
commit d29e76937c
10 changed files with 315 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/main/main.cpp
View File

@@ -198,15 +198,6 @@ int main(int argc, char ** argv) {
params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
}
// export the cgraph and exit
if (params.export_cgraph) {
llama_eval_export(ctx, "llama.ggml");
llama_free(ctx);
llama_free_model(model);
return 0;
}
std::string path_session = params.path_prompt_cache;
std::vector<llama_token> session_tokens;