biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Use smaller embedding model when not testing model specifically (#13891)

Browse Source
This commit is contained in:
Harry Mellor
2025-02-28 08:50:43 +00:00
committed by GitHub
parent b9e41734c5
commit 76c89fcadd
9 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/entrypoints/openai/test_embedding.py
View File

@@ -13,7 +13,7 @@ from vllm.transformers_utils.tokenizer import get_tokenizer
from ...utils import RemoteOpenAIServer
MODEL_NAME = "intfloat/e5-mistral-7b-instruct"
MODEL_NAME = "intfloat/multilingual-e5-small"
DUMMY_CHAT_TEMPLATE = """{% for message in messages %}{{message['role'] + ': ' + message['content'] + '\\n'}}{% endfor %}""" # noqa: E501

4
tests/entrypoints/openai/test_metrics.py
View File

@@ -282,7 +282,7 @@ async def test_metrics_exist(server: RemoteOpenAIServer,
def test_metrics_exist_run_batch(use_v1: bool):
if use_v1:
pytest.skip("Skipping test on vllm V1")
input_batch = """{"custom_id": "request-0", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are a helpful assistant."}}""" # noqa: E501
input_batch = """{"custom_id": "request-0", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/multilingual-e5-small", "input": "You are a helpful assistant."}}""" # noqa: E501
base_url = "0.0.0.0"
port = "8001"
@@ -302,7 +302,7 @@ def test_metrics_exist_run_batch(use_v1: bool):
"-o",
output_file.name,
"--model",
"intfloat/e5-mistral-7b-instruct",
"intfloat/multilingual-e5-small",
"--enable-metrics",
"--url",
base_url,

10
tests/entrypoints/openai/test_run_batch.py
View File

@@ -18,10 +18,10 @@ INPUT_BATCH = """{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/c
INVALID_INPUT_BATCH = """{"invalid_field": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "NousResearch/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "NousResearch/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}"""
INPUT_EMBEDDING_BATCH = """{"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are a helpful assistant."}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are an unhelpful assistant."}}
INPUT_EMBEDDING_BATCH = """{"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/multilingual-e5-small", "input": "You are a helpful assistant."}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/multilingual-e5-small", "input": "You are an unhelpful assistant."}}
{"custom_id": "request-3", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "Hello world!"}}
{"custom_id": "request-3", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/multilingual-e5-small", "input": "Hello world!"}}
{"custom_id": "request-4", "method": "POST", "url": "/v1/embeddings", "body": {"model": "NonExistModel", "input": "Hello world!"}}"""
INPUT_SCORE_BATCH = """{"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
@@ -37,7 +37,7 @@ def test_empty_file():
proc = subprocess.Popen([
sys.executable, "-m", "vllm.entrypoints.openai.run_batch", "-i",
input_file.name, "-o", output_file.name, "--model",
"intfloat/e5-mistral-7b-instruct"
"intfloat/multilingual-e5-small"
], )
proc.communicate()
proc.wait()
@@ -97,7 +97,7 @@ def test_embeddings():
proc = subprocess.Popen([
sys.executable, "-m", "vllm.entrypoints.openai.run_batch", "-i",
input_file.name, "-o", output_file.name, "--model",
"intfloat/e5-mistral-7b-instruct"
"intfloat/multilingual-e5-small"
], )
proc.communicate()
proc.wait()