LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

server: fix double submits of infill (#1944)

Browse Source 
Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2026-06-10 07:48:15 +02:00
committed by GitHub
co-authored by firecoperana <firecoperana>
parent 71d5aa21f7
commit 2a1148384c
5 changed files with 14 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/server/server.cpp
+5 -4
View File
@@ -1358,10 +1358,11 @@ int main(int argc, char ** argv) {
const auto handle_infill = [&ctx_server, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) {
log_prompt(ctx_server.params_base, json::parse(req.body));
json data = json::parse(req.body);
const int id_task = ctx_server.queue_tasks.get_new_id();
server_tokens token; // dummy tokens
ctx_server.queue_results.add_waiting_task_id(id_task);
ctx_server.request_completion(id_task, -1, data, true, false, std::move(token));
//avoid double submits
//const int id_task = ctx_server.queue_tasks.get_new_id();
//server_tokens token; // dummy tokens
//ctx_server.queue_results.add_waiting_task_id(id_task);
//ctx_server.request_completion(id_task, -1, data, true, false, token);
std::vector<raw_buffer> files; // dummy
handle_completions_impl(
SERVER_TASK_TYPE_INFILL,