kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-11 05:30:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: (router) add model management API (#23976)

Browse Source 
* wip

* server: (router) add SSE realtime updates API

* nits

* wip

* add download API

* add download api

* update docs

* add delete endpoint

* fix std::terminate

* fix crash

* fix 2

* add tests

* nits
This commit is contained in:
Xuan-Son Nguyen
2026-06-17 18:04:58 +02:00
committed by GitHub
parent b4024af6c2
commit 4b4d13ae72
16 changed files with 855 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-queue.cpp
+11
View File
@@ -331,6 +331,17 @@ void server_response::send(server_task_result_ptr && result) {
}
}
void server_response::broadcast(server_task_result_ptr && result) {
std::unique_lock<std::mutex> lock(mutex_results);
for (const auto & id_task : waiting_task_ids) {
RES_DBG("task id = %d pushed to result queue\n", id_task);
server_task_result_ptr res_copy(result->clone());
res_copy->id = id_task; // override id with target task id
queue_results.emplace_back(std::move(res_copy));
}
condition_results.notify_all();
}
void server_response::terminate() {
running = false;
condition_results.notify_all();