[V1] V1 Enablement Oracle (#13726)
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
@@ -10,7 +10,6 @@ from ...utils import RemoteOpenAIServer
|
||||
|
||||
# # any model with a chat template should work here
|
||||
MODEL_NAME = "Qwen/Qwen2-1.5B-Instruct"
|
||||
DUMMY_CHAT_TEMPLATE = """{% for message in messages %}{{message['role'] + ': ' + message['content'] + '\\n'}}{% endfor %}""" # noqa: E501
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
@@ -22,8 +21,6 @@ def server():
|
||||
"--enforce-eager",
|
||||
"--max-model-len",
|
||||
"4080",
|
||||
"--chat-template",
|
||||
DUMMY_CHAT_TEMPLATE,
|
||||
]
|
||||
|
||||
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
|
||||
|
||||
Reference in New Issue
Block a user