tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 22:36:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : better security control for public deployments (#9776)

Browse Source 
* server : more explicit endpoint access settings

* protect /props endpoint

* fix tests

* update server docs

* fix typo

* fix tests
This commit is contained in:
Xuan Son Nguyen
2024-10-08 13:27:04 +02:00
committed by GitHub
parent fa42aa6d89
commit 458367a906
8 changed files with 126 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
common/arg.cpp
View File

@@ -1838,9 +1838,23 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
params.endpoint_metrics = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_METRICS"));
add_opt(llama_arg(
{"--slots"},
format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
[](gpt_params & params) {
params.endpoint_slots = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
add_opt(llama_arg(
{"--props"},
format("enable changing global properties via POST /props (default: %s)", params.endpoint_props ? "enabled" : "disabled"),
[](gpt_params & params) {
params.endpoint_props = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_PROPS"));
add_opt(llama_arg(
{"--no-slots"},
format("disables slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
"disables slots monitoring endpoint",
[](gpt_params & params) {
params.endpoint_slots = false;
}