feat: use llama.cpp server

engine/e2e-test/api/engines/test_api_engine.py

@@ -28,14 +28,14 @@ def test_engines_get_llamacpp_should_be_successful(self):
 
     # engines install
     def test_engines_install_llamacpp_specific_version_and_variant(self):
-        data = {"version": "b4920", "variant": "linux-avx-x64"}
+        data = {"version": "b4932", "variant": "linux-avx-x64"}
         response = requests.post(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data
         )
         assert response.status_code == 200
 
     def test_engines_install_llamacpp_specific_version_and_null_variant(self):
-        data = {"version": "b4920"}
+        data = {"version": "b4932"}
         response = requests.post(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data
         )
@@ -62,7 +62,7 @@ async def test_engines_install_uninstall_llamacpp_with_only_version_should_be_fa
         await wait_for_websocket_download_success_event(timeout=120)
         assert install_response.status_code == 200
 
-        data = {"version": "b4920"}
+        data = {"version": "b4932"}
         response = requests.delete(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data
         )
@@ -85,7 +85,7 @@ async def test_engines_install_uninstall_llamacpp_with_variant_should_be_success
     def test_engines_install_uninstall_llamacpp_with_specific_variant_and_version_should_be_successful(
         self,
     ):
-        data = {"variant": "linux-avx-x64", "version": "b4920"}
+        data = {"variant": "linux-avx-x64", "version": "b4932"}
         # install first
         install_response = requests.post(
             "http://localhost:3928/v1/engines/llama-cpp/install", json=data

engine/e2e-test/api/engines/test_api_get_default_engine.py

@@ -25,7 +25,7 @@ def test_api_get_default_engine_successfully(self):
         # Data test
         engine= "llama-cpp"
         name= "linux-avx-x64"
-        version= "b4920"
+        version= "b4932"
 
         data = {"version": version, "variant": name}
         post_install_url = f"http://localhost:3928/v1/engines/{engine}/install"

engine/e2e-test/api/engines/test_api_get_list_engine.py

@@ -25,7 +25,7 @@ def test_api_get_list_engines_successfully(self):
         # Data test
         engine= "llama-cpp"
         name= "linux-avx-x64"
-        version= "b4920"
+        version= "b4932"
 
         post_install_url = f"http://localhost:3928/v1/engines/{engine}/install"
         response = requests.delete(

engine/e2e-test/api/engines/test_api_post_default_engine.py

@@ -24,7 +24,7 @@ def test_api_set_default_engine_successfully(self):
         # Data test
         engine= "llama-cpp"
         name= "linux-avx-x64"
-        version= "b4920"
+        version= "b4932"
 
         data = {"version": version, "variant": name}
         post_install_url = f"http://localhost:3928/v1/engines/{engine}/install"

engine/e2e-test/cli/engines/test_cli_engine_install.py

@@ -33,7 +33,7 @@ def test_engines_install_llamacpp_should_be_successfully(self):
 
     @pytest.mark.skipif(platform.system() == "Windows", reason="Progress bar log issue on Windows")
     def test_engines_install_pre_release_llamacpp(self):
-        engine_version = "b4920"
+        engine_version = "b4932"
         exit_code, output, error = run(
             "Install Engine",
             ["engines", "install", "llama-cpp", "-v", engine_version],