root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 19:34:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

server: Improve wording to make clear that standby-timeout is measured in seconds

Browse Source
This commit is contained in:
johannes 2024-12-09 23:55:22 +01:00
parent 9a8df14d5c
commit 0468a01c9c
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@ -1787,7 +1787,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CACHE_REUSE")); ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CACHE_REUSE"));
add_opt(common_arg( add_opt(common_arg(
{"--standby-timeout"}, "N", {"--standby-timeout"}, "N",
string_format("time that must pass since a request has been served, before the server stops automatically (default: %d)", params.standby_timeout), string_format("seconds that must pass since a request has been served, before the server stops automatically (default: %d)", params.standby_timeout),
[](common_params & params, int value) { [](common_params & params, int value) {
params.standby_timeout = value; params.standby_timeout = value;
} }

2
common/common.h
View File

@ -306,7 +306,7 @@ struct common_params {
int32_t timeout_write = timeout_read; // http write timeout in seconds int32_t timeout_write = timeout_read; // http write timeout in seconds
int32_t n_threads_http = -1; // number of threads to process HTTP requests (TODO: support threadpool) int32_t n_threads_http = -1; // number of threads to process HTTP requests (TODO: support threadpool)
int32_t n_cache_reuse = 0; // min chunk size to reuse from the cache via KV shifting int32_t n_cache_reuse = 0; // min chunk size to reuse from the cache via KV shifting
int32_t standby_timeout = 0; // time that must pass since a request has been processed before server terminates in order to save resources. If -1, then never terminate automatically. int32_t standby_timeout = 0; // seconds that must pass since a request has been processed before server terminates in order to save resources. If -1, then never terminate automatically.
std::string hostname = "127.0.0.1"; std::string hostname = "127.0.0.1";
std::string public_path = ""; // NOLINT std::string public_path = ""; // NOLINT