[ci] try to add multi-node tests (#6280)
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai> Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
This commit is contained in:
@@ -3,33 +3,26 @@ import base64
|
||||
import numpy as np
|
||||
import openai
|
||||
import pytest
|
||||
import ray
|
||||
|
||||
from ...utils import VLLM_PATH, RemoteOpenAIServer
|
||||
from ...utils import RemoteOpenAIServer
|
||||
|
||||
EMBEDDING_MODEL_NAME = "intfloat/e5-mistral-7b-instruct"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def ray_ctx():
|
||||
ray.init(runtime_env={"working_dir": VLLM_PATH})
|
||||
yield
|
||||
ray.shutdown()
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def embedding_server(ray_ctx):
|
||||
return RemoteOpenAIServer([
|
||||
"--model",
|
||||
EMBEDDING_MODEL_NAME,
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
"bfloat16",
|
||||
"--enforce-eager",
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
"--enforce-eager",
|
||||
])
|
||||
def embedding_server():
|
||||
with RemoteOpenAIServer([
|
||||
"--model",
|
||||
EMBEDDING_MODEL_NAME,
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
"bfloat16",
|
||||
"--enforce-eager",
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
"--enforce-eager",
|
||||
]) as remote_server:
|
||||
yield remote_server
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
Reference in New Issue
Block a user