vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-30 20:33:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

server: bump timeout to 3600s (#23842)

Browse source 
* server: bump timeout to 3600s

* nits: change wording
This commit is contained in:
Xuan-Son Nguyen 2026-05-29 10:23:17 +02:00 • committed by GitHub
parent 1f0aa2a696
commit cb47092b00
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.h
View file

@ -587,7 +587,7 @@ struct common_params {
// server params
int32_t port = 8080; // server listens on this network port
bool reuse_port = false; // allow multiple sockets to bind to the same port
int32_t timeout_read = 600; // http read timeout in seconds
int32_t timeout_read = 3600; // http read 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_cache_reuse = 0; // min chunk size to reuse from the cache via KV shifting

6
tools/server/server-queue.cpp
View file

@ -381,8 +381,10 @@ server_task_result_ptr server_response_reader::next(const std::function<bool()>
if (result == nullptr) {
// timeout, check stop condition
if (should_stop()) {
SRV_WRN("%s", "stopping wait for next result due to should_stop condition (adjust the --timeout argument if needed)\n");
SRV_WRN("%s", "ref: https://github.com/ggml-org/llama.cpp/pull/22907\n");
const int64_t time_elapsed_ms = ggml_time_ms() - time_start_ms;
if (time_elapsed_ms > 30000) {
SRV_WRN("%s", "request cancelled after 30s, potentially a client-side timeout; please check your client's code\n");
}
return nullptr;
}
} else {

2
tools/server/server-queue.h
View file

@ -169,6 +169,8 @@ struct server_response_reader {
bool cancelled = false;
int polling_interval_seconds;
const int64_t time_start_ms = ggml_time_ms();
// tracking generation state and partial tool calls
// only used by streaming completions
std::vector<task_result_state> states;