mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-12 03:31:46 +00:00
server : fix --threads-http arg (#7801)
This commit is contained in:
parent
f83351f9a6
commit
ee459f40f6
@ -1414,6 +1414,14 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
|||||||
params.timeout_write = std::stoi(argv[i]);
|
params.timeout_write = std::stoi(argv[i]);
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
if (arg == "--threads-http") {
|
||||||
|
if (++i >= argc) {
|
||||||
|
invalid_param = true;
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
params.n_threads_http = std::stoi(argv[i]);
|
||||||
|
return true;
|
||||||
|
}
|
||||||
if (arg == "-spf" || arg == "--system-prompt-file") {
|
if (arg == "-spf" || arg == "--system-prompt-file") {
|
||||||
if (++i >= argc) {
|
if (++i >= argc) {
|
||||||
invalid_param = true;
|
invalid_param = true;
|
||||||
@ -1893,6 +1901,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
|
|||||||
options.push_back({ "server", " --ssl-key-file FNAME", "path to file a PEM-encoded SSL private key" });
|
options.push_back({ "server", " --ssl-key-file FNAME", "path to file a PEM-encoded SSL private key" });
|
||||||
options.push_back({ "server", " --ssl-cert-file FNAME", "path to file a PEM-encoded SSL certificate" });
|
options.push_back({ "server", " --ssl-cert-file FNAME", "path to file a PEM-encoded SSL certificate" });
|
||||||
options.push_back({ "server", " --timeout N", "server read/write timeout in seconds (default: %d)", params.timeout_read });
|
options.push_back({ "server", " --timeout N", "server read/write timeout in seconds (default: %d)", params.timeout_read });
|
||||||
|
options.push_back({ "server", " --threads-http N", "number of threads used to process HTTP requests (default: %d)", params.n_threads_http });
|
||||||
options.push_back({ "server", " --system-prompt-file FNAME",
|
options.push_back({ "server", " --system-prompt-file FNAME",
|
||||||
"set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications" });
|
"set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications" });
|
||||||
options.push_back({ "server", " --log-format {text,json}",
|
options.push_back({ "server", " --log-format {text,json}",
|
||||||
|
@ -184,7 +184,7 @@ struct gpt_params {
|
|||||||
int32_t port = 8080; // server listens on this network port
|
int32_t port = 8080; // server listens on this network port
|
||||||
int32_t timeout_read = 600; // http read timeout in seconds
|
int32_t timeout_read = 600; // http read timeout in seconds
|
||||||
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 use for http server (-1 = use n_threads)
|
int32_t n_threads_http = -1; // number of threads to process HTTP requests
|
||||||
|
|
||||||
std::string hostname = "127.0.0.1";
|
std::string hostname = "127.0.0.1";
|
||||||
std::string public_path = "";
|
std::string public_path = "";
|
||||||
|
Loading…
Reference in New Issue
Block a user