mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-14 06:34:58 +08:00
e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
124 lines
4.3 KiB
Python
124 lines
4.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import pytest
|
|
import requests
|
|
|
|
from vllm.entrypoints.openai.protocol import ScoreResponse
|
|
|
|
from ...utils import RemoteOpenAIServer
|
|
|
|
MODEL_NAME = "BAAI/bge-reranker-v2-m3"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def server():
|
|
args = ["--enforce-eager", "--max-model-len", "100"]
|
|
|
|
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
|
|
yield remote_server
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model_name", [MODEL_NAME])
|
|
def test_text_1_str_text_2_list(server: RemoteOpenAIServer, model_name: str):
|
|
text_1 = "What is the capital of France?"
|
|
text_2 = [
|
|
"The capital of Brazil is Brasilia.", "The capital of France is Paris."
|
|
]
|
|
|
|
score_response = requests.post(server.url_for("score"),
|
|
json={
|
|
"model": model_name,
|
|
"text_1": text_1,
|
|
"text_2": text_2,
|
|
})
|
|
score_response.raise_for_status()
|
|
score = ScoreResponse.model_validate(score_response.json())
|
|
|
|
assert score.id is not None
|
|
assert score.data is not None
|
|
assert len(score.data) == 2
|
|
assert score.data[0].score <= 0.01
|
|
assert score.data[1].score >= 0.9
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model_name", [MODEL_NAME])
|
|
def test_text_1_list_text_2_list(server: RemoteOpenAIServer, model_name: str):
|
|
text_1 = [
|
|
"What is the capital of the United States?",
|
|
"What is the capital of France?"
|
|
]
|
|
text_2 = [
|
|
"The capital of Brazil is Brasilia.", "The capital of France is Paris."
|
|
]
|
|
|
|
score_response = requests.post(server.url_for("score"),
|
|
json={
|
|
"model": model_name,
|
|
"text_1": text_1,
|
|
"text_2": text_2,
|
|
})
|
|
score_response.raise_for_status()
|
|
score = ScoreResponse.model_validate(score_response.json())
|
|
|
|
assert score.id is not None
|
|
assert score.data is not None
|
|
assert len(score.data) == 2
|
|
assert score.data[0].score <= 0.01
|
|
assert score.data[1].score >= 0.9
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model_name", [MODEL_NAME])
|
|
def test_text_1_str_text_2_str(server: RemoteOpenAIServer, model_name: str):
|
|
text_1 = "What is the capital of France?"
|
|
text_2 = "The capital of France is Paris."
|
|
|
|
score_response = requests.post(server.url_for("score"),
|
|
json={
|
|
"model": model_name,
|
|
"text_1": text_1,
|
|
"text_2": text_2,
|
|
})
|
|
score_response.raise_for_status()
|
|
score = ScoreResponse.model_validate(score_response.json())
|
|
|
|
assert score.id is not None
|
|
assert score.data is not None
|
|
assert len(score.data) == 1
|
|
assert score.data[0].score >= 0.9
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model_name", [MODEL_NAME])
|
|
def test_score_max_model_len(server: RemoteOpenAIServer, model_name: str):
|
|
|
|
text_1 = "What is the capital of France?" * 20
|
|
text_2 = [
|
|
"The capital of Brazil is Brasilia.", "The capital of France is Paris."
|
|
]
|
|
|
|
score_response = requests.post(server.url_for("score"),
|
|
json={
|
|
"model": model_name,
|
|
"text_1": text_1,
|
|
"text_2": text_2,
|
|
})
|
|
assert score_response.status_code == 400
|
|
# Assert just a small fragments of the response
|
|
assert "Please reduce the length of the input." in \
|
|
score_response.text
|
|
|
|
# Test truncation
|
|
score_response = requests.post(server.url_for("score"),
|
|
json={
|
|
"model": model_name,
|
|
"text_1": text_1,
|
|
"text_2": text_2,
|
|
"truncate_prompt_tokens": 101
|
|
})
|
|
assert score_response.status_code == 400
|
|
assert "Please, select a smaller truncation size." in \
|
|
score_response.text
|