wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-29 17:17:40 +02:00
Code Issues Packages Projects Releases Wiki Activity

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
3 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-queue.cpp
+4 -2
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 {