server : add more test cases (#10569)

* server : add split model test

* add test speculative

* add invalid cases

examples/server/tests/unit/test_basic.py

@@ -32,3 +32,17 @@ def test_server_models():
     assert res.status_code == 200
     assert len(res.body["data"]) == 1
     assert res.body["data"][0]["id"] == server.model_alias
+
+def test_load_split_model():
+    global server
+    server.model_hf_repo = "ggml-org/models"
+    server.model_hf_file = "tinyllamas/split/stories15M-q8_0-00001-of-00003.gguf"
+    server.model_alias = "tinyllama-split"
+    server.start()
+    res = server.make_request("POST", "/completion", data={
+        "n_predict": 16,
+        "prompt": "Hello",
+        "temperature": 0.0,
+    })
+    assert res.status_code == 200
+    assert match_regex("(little|girl)+", res.body["content"])