feat(ci): llama3 test working

backends/gaudi/Makefile

@@ -54,7 +54,7 @@ run-integration-tests:
 	uv pip install -r ${root_dir}/backends/gaudi/server/integration-tests/requirements.txt
 	DOCKER_VOLUME=${root_dir}/data \
 	HF_TOKEN=`cat ${HOME}/.cache/huggingface/token` \
-    pytest --durations=0 -s -vv integration-tests --gaudi
+    pytest --durations=0 -s -vv ${root_dir}/integration-tests --gaudi
 
 # This is used to capture the expected outputs for the integration tests offering an easy way to add more models to the integration tests
 capture-expected-outputs-for-integration-tests:

integration-tests/conftest.py

@@ -1,4 +1,8 @@
-pytest_plugins = ["fixtures.neuron.service", "fixtures.neuron.export_models"]
+pytest_plugins = [
+    "fixtures.neuron.service",
+    "fixtures.neuron.export_models",
+    "fixtures.gaudi.service",
+]
 # ruff: noqa: E402
 from _pytest.fixtures import SubRequest
 from huggingface_hub.inference._generated.types.chat_completion import (

integration-tests/fixtures/gaudi/service.py

@@ -15,9 +15,10 @@ import pytest
 from aiohttp import ClientConnectorError, ClientOSError, ServerDisconnectedError
 from docker.errors import NotFound
 import logging
-from gaudi.test_generate import TEST_CONFIGS
+from gaudi.test_gaudi_generate import TEST_CONFIGS
 from text_generation import AsyncClient
 from text_generation.types import Response
+import huggingface_hub
 
 logging.basicConfig(
     level=logging.INFO,
@@ -29,7 +30,7 @@ logger = logging.getLogger(__file__)
 # Use the latest image from the local docker build
 DOCKER_IMAGE = os.getenv("DOCKER_IMAGE", "tgi-gaudi")
 DOCKER_VOLUME = os.getenv("DOCKER_VOLUME", None)
-HF_TOKEN = os.getenv("HF_TOKEN", None)
+HF_TOKEN = huggingface_hub.get_token()
 
 assert (
     HF_TOKEN is not None
@@ -152,7 +153,7 @@ def data_volume():
 
 
 @pytest.fixture(scope="module")
-def launcher(data_volume):
+def gaudi_launcher(event_loop):
     @contextlib.contextmanager
     def docker_launcher(
         model_id: str,
@@ -272,7 +273,7 @@ def launcher(data_volume):
 
 
 @pytest.fixture(scope="module")
-def generate_load():
+def gaudi_generate_load():
     async def generate_load_inner(
         client: AsyncClient, prompt: str, max_new_tokens: int, n: int
     ) -> List[Response]: