LLM inference in C/C++
C++ ggml
server: temporary skip model downloading API test (#25355)
Xuan-Son Nguyenbfdf581b8b2a
diff --git a/tools/server/tests/unit/test_router.py b/tools/server/tests/unit/test_router.pyindex 94165e520e..cdd6f53144 100644--- a/tools/server/tests/unit/test_router.py+++ b/tools/server/tests/unit/test_router.py@@ -314,6 +314,7 @@ def _wait_for_sse_event(collected: list, event_type: str, model: str, timeout: ireturn False[email protected](reason="sse_thread sometimes hangs on GH actions, to be investigated")def test_router_download_model():"""Case 1: download a model, verify SSE events and GET /models."""global server@@ -357,6 +358,7 @@ def test_router_download_model():assert MODEL_DOWNLOAD_ID in ids, f"{MODEL_DOWNLOAD_ID} not found in /models after download"[email protected](reason="sse_thread sometimes hangs on GH actions, to be investigated")def test_router_delete_model():"""Case 2: delete the downloaded model, verify it disappears from GET /models."""global server