Skip to content

LLM inference in C/C++

C++ ggml

server : do not forward --api-key-file to router-spawned child instances (#28938)

Nandan Vallamdasu982a3329af84
diff --git a/tools/server/server-models.cpp b/tools/server/server-models.cpp
index b10d9bd8a6..9c00036e02 100644
--- a/tools/server/server-models.cpp
+++ b/tools/server/server-models.cpp
@@ -470,6 +470,7 @@ static void unset_reserved_args(common_preset & preset, bool unset_model_args) {
preset.unset_option("LLAMA_ARG_SSL_KEY_FILE");
preset.unset_option("LLAMA_ARG_SSL_CERT_FILE");
preset.unset_option("LLAMA_API_KEY");
+ preset.unset_option("LLAMA_ARG_API_KEY_FILE");
preset.unset_option("LLAMA_ARG_MODELS_DIR");
preset.unset_option("LLAMA_ARG_MODELS_MAX");
preset.unset_option("LLAMA_ARG_MODELS_PRESET");