diff --git a/litellm/proxy/_super_secret_config.yaml b/litellm/proxy/_super_secret_config.yaml index 2e8183cb2d5..0e1b4b2e136 100644 --- a/litellm/proxy/_super_secret_config.yaml +++ b/litellm/proxy/_super_secret_config.yaml @@ -4,5 +4,20 @@ model_list: api_key: my-fake-key model: openai/my-fake-model model_name: fake-openai-endpoint +- litellm_params: + api_base: http://0.0.0.0:8080 + api_key: my-fake-key + model: openai/my-fake-model-2 + model_name: fake-openai-endpoint +- litellm_params: + api_base: http://0.0.0.0:8080 + api_key: my-fake-key + model: openai/my-fake-model-3 + model_name: fake-openai-endpoint +- litellm_params: + api_base: http://0.0.0.0:8080 + api_key: my-fake-key + model: openai/my-fake-model-4 + model_name: fake-openai-endpoint router_settings: num_retries: 0 \ No newline at end of file diff --git a/litellm/tests/test_least_busy_routing.py b/litellm/tests/test_least_busy_routing.py index 782d5b343a6..cb9d59e7557 100644 --- a/litellm/tests/test_least_busy_routing.py +++ b/litellm/tests/test_least_busy_routing.py @@ -201,6 +201,7 @@ async def test_router_atext_completion_streaming(): @pytest.mark.asyncio async def test_router_completion_streaming(): + litellm.set_verbose = True messages = [ {"role": "user", "content": "Hello, can you generate a 500 words poem?"} ] @@ -219,9 +220,9 @@ async def test_router_completion_streaming(): { "model_name": "azure-model", "litellm_params": { - "model": "azure/gpt-35-turbo", - "api_key": "os.environ/AZURE_EUROPE_API_KEY", - "api_base": "https://my-endpoint-europe-berri-992.openai.azure.com", + "model": "azure/gpt-turbo", + "api_key": "os.environ/AZURE_FRANCE_API_KEY", + "api_base": "https://openai-france-1234.openai.azure.com", "rpm": 6, }, "model_info": {"id": 2}, @@ -229,9 +230,9 @@ async def test_router_completion_streaming(): { "model_name": "azure-model", "litellm_params": { - "model": "azure/gpt-35-turbo", - "api_key": "os.environ/AZURE_CANADA_API_KEY", - "api_base": "https://my-endpoint-canada-berri992.openai.azure.com", + "model": "azure/gpt-turbo", + "api_key": "os.environ/AZURE_FRANCE_API_KEY", + "api_base": "https://openai-france-1234.openai.azure.com", "rpm": 6, }, "model_info": {"id": 3}, @@ -262,4 +263,4 @@ async def test_router_completion_streaming(): ## check if calls equally distributed cache_dict = router.cache.get_cache(key=cache_key) for k, v in cache_dict.items(): - assert v == 1 + assert v == 1, f"Failed. K={k} called v={v} times, cache_dict={cache_dict}"