[Chore] Remove unused noqas (#31263)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
+1
-1
@@ -410,7 +410,7 @@ class HfRunner:
|
||||
|
||||
# don't put this import at the top level
|
||||
# it will call torch.cuda.device_count()
|
||||
from transformers import AutoProcessor # noqa: F401
|
||||
from transformers import AutoProcessor
|
||||
|
||||
self.processor = AutoProcessor.from_pretrained(
|
||||
model_name,
|
||||
|
||||
@@ -15,7 +15,7 @@ MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(): # noqa: F811
|
||||
def server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
|
||||
@@ -28,7 +28,7 @@ def zephyr_lora_files():
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(zephyr_lora_files): # noqa: F811
|
||||
def server(zephyr_lora_files):
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
|
||||
@@ -12,7 +12,7 @@ MODEL_NAME = "Qwen/QwQ-32B"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(): # noqa: F811
|
||||
def server():
|
||||
args = [
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
|
||||
@@ -125,7 +125,7 @@ messages = [
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(): # noqa: F811
|
||||
def server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
@@ -212,7 +212,7 @@ async def test_function_tool_use(
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def k2_server(): # noqa: F811
|
||||
def k2_server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
|
||||
@@ -23,7 +23,7 @@ ACTIVE_MM_LORA_RESPONSE = "Spoken text: The first words I spoke in the original
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def multimodal_server(): # noqa: F811
|
||||
def multimodal_server():
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
|
||||
@@ -8,7 +8,7 @@ from ...utils import RemoteOpenAIServer
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def chat_server_with_force_include_usage(request): # noqa: F811
|
||||
def chat_server_with_force_include_usage(request):
|
||||
args = [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
|
||||
@@ -11,7 +11,7 @@ MODEL_NAME = "Qwen/Qwen3-0.6B"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server(): # noqa: F811
|
||||
def server():
|
||||
args = [
|
||||
"--max-model-len",
|
||||
"2048",
|
||||
|
||||
@@ -37,7 +37,7 @@ def default_server_args(qwen3_lora_files):
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server_fixture(request, default_server_args): # noqa: F811
|
||||
def server_fixture(request, default_server_args):
|
||||
use_server_flag = request.param
|
||||
if use_server_flag:
|
||||
args_with_flag = default_server_args + ["--return-tokens-as-token-ids"]
|
||||
|
||||
@@ -267,7 +267,7 @@ def run_embedding_input_test(
|
||||
"""Inference result should be the same between
|
||||
original image/video input and image/video embeddings input.
|
||||
"""
|
||||
from transformers import AutoProcessor # noqa: F401
|
||||
from transformers import AutoProcessor
|
||||
|
||||
processor = AutoProcessor.from_pretrained(model)
|
||||
|
||||
|
||||
@@ -145,7 +145,7 @@ def test_shared_storage_connector_hashes(tmp_path):
|
||||
|
||||
# don't put this import at the top level
|
||||
# it will call torch.cuda.device_count()
|
||||
from transformers import AutoProcessor # noqa: F401
|
||||
from transformers import AutoProcessor
|
||||
|
||||
# Create processor to handle the chat prompt
|
||||
processor = AutoProcessor.from_pretrained(MODEL_NAME)
|
||||
|
||||
Reference in New Issue
Block a user