Skip to content

LLM inference in C/C++

C++ ggml

cli: fix model params not propagated (#23893)

therealkenc86591c7536ce
diff --git a/tools/cli/cli.cpp b/tools/cli/cli.cpp
index af40adbb4c..e830f262de 100644
--- a/tools/cli/cli.cpp
+++ b/tools/cli/cli.cpp
@@ -397,6 +397,8 @@ int llama_cli(int argc, char ** argv) {
return 1;
}
+ ctx_cli.defaults.sampling = params.sampling;
+
console::spinner::stop();
console::log("\n");