CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : enable /slots by default and make it secure (#15630)

Browse Source 
* server : enable /slots by default and make it secure

ggml-ci

* server : fix tests to pass `--no-slots` when necessary

* server : extend /props with info about enabled endpoints
This commit is contained in:
Georgi Gerganov
2025-08-31 20:11:58 +03:00
committed by GitHub
parent 4efd5a8316
commit 0d161f021a
5 changed files with 200 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
common/arg.cpp
View File

@@ -2962,13 +2962,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.endpoint_metrics = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_METRICS"));
add_opt(common_arg(
{"--slots"},
string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
[](common_params & params) {
params.endpoint_slots = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
add_opt(common_arg(
{"--props"},
string_format("enable changing global properties via POST /props (default: %s)", params.endpoint_props ? "enabled" : "disabled"),
@@ -2976,6 +2969,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.endpoint_props = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_PROPS"));
add_opt(common_arg(
{"--slots"},
string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
[](common_params & params) {
params.endpoint_slots = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
add_opt(common_arg(
{"--no-slots"},
"disables slots monitoring endpoint",