[Bugfix] Fix Qwen3-VL-Reranker load. (#33298)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io> Signed-off-by: wang.yuqi <noooop@126.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent
2515bbd027
commit
abb34ac43a
@@ -5,9 +5,9 @@ import json
|
||||
import pytest
|
||||
import requests
|
||||
|
||||
from tests.entrypoints.test_utils import encode_base64_content_from_url
|
||||
from tests.utils import RemoteOpenAIServer
|
||||
from vllm.entrypoints.pooling.classify.protocol import ClassificationResponse
|
||||
from vllm.multimodal.utils import encode_image_url, fetch_image
|
||||
|
||||
MODEL_NAME = "muziyongshixin/Qwen2.5-VL-7B-for-VideoCls"
|
||||
MAXIMUM_VIDEOS = 1
|
||||
@@ -19,7 +19,7 @@ HF_OVERRIDES = {
|
||||
}
|
||||
input_text = "This product was excellent and exceeded my expectations"
|
||||
image_url = "https://vllm-public-assets.s3.us-west-2.amazonaws.com/multimodal_asset/cat_snow.jpg"
|
||||
image_base64 = encode_base64_content_from_url(image_url)
|
||||
image_base64 = {"url": encode_image_url(fetch_image(image_url))}
|
||||
video_url = "https://www.bogotobogo.com/python/OpenCV_Python/images/mean_shift_tracking/slow_traffic_small.mp4"
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,122 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
import requests
|
||||
|
||||
from tests.utils import VLLM_PATH, RemoteOpenAIServer
|
||||
from vllm.entrypoints.pooling.score.protocol import ScoreResponse
|
||||
from vllm.multimodal.utils import encode_image_url, fetch_image
|
||||
|
||||
MODEL_NAME = "Qwen/Qwen3-VL-Reranker-2B"
|
||||
HF_OVERRIDES = {
|
||||
"architectures": ["Qwen3VLForSequenceClassification"],
|
||||
"classifier_from_token": ["no", "yes"],
|
||||
"is_original_qwen3_reranker": True,
|
||||
}
|
||||
|
||||
query = "A cat standing in the snow."
|
||||
image_url = "https://vllm-public-assets.s3.us-west-2.amazonaws.com/multimodal_asset/cat_snow.jpg"
|
||||
documents = [
|
||||
{
|
||||
"type": "text",
|
||||
"text": query,
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {"url": image_url},
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {"url": encode_image_url(fetch_image(image_url))},
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def server():
|
||||
args = [
|
||||
"--enforce-eager",
|
||||
"--max-model-len",
|
||||
"8192",
|
||||
"--chat-template",
|
||||
str(VLLM_PATH / "examples/pooling/score/template/qwen3_vl_reranker.jinja"),
|
||||
]
|
||||
|
||||
with RemoteOpenAIServer(
|
||||
MODEL_NAME, args, override_hf_configs=HF_OVERRIDES
|
||||
) as remote_server:
|
||||
yield remote_server
|
||||
|
||||
|
||||
def test_score_api_queries_str_documents_str(server: RemoteOpenAIServer):
|
||||
queries = "What is the capital of France?"
|
||||
documents = "The capital of France is Paris."
|
||||
|
||||
score_response = requests.post(
|
||||
server.url_for("score"),
|
||||
json={
|
||||
"model": MODEL_NAME,
|
||||
"queries": queries,
|
||||
"documents": documents,
|
||||
},
|
||||
)
|
||||
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
|
||||
|
||||
|
||||
def test_score_api_queries_str_documents_text_content(server: RemoteOpenAIServer):
|
||||
score_response = requests.post(
|
||||
server.url_for("score"),
|
||||
json={
|
||||
"model": MODEL_NAME,
|
||||
"queries": query,
|
||||
"documents": {"content": [documents[0]]},
|
||||
},
|
||||
)
|
||||
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
|
||||
|
||||
|
||||
def test_score_api_queries_str_documents_image_url_content(server: RemoteOpenAIServer):
|
||||
score_response = requests.post(
|
||||
server.url_for("score"),
|
||||
json={
|
||||
"model": MODEL_NAME,
|
||||
"queries": query,
|
||||
"documents": {"content": [documents[1]]},
|
||||
},
|
||||
)
|
||||
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
|
||||
|
||||
|
||||
def test_score_api_queries_str_documents_image_base64_content(
|
||||
server: RemoteOpenAIServer,
|
||||
):
|
||||
score_response = requests.post(
|
||||
server.url_for("score"),
|
||||
json={
|
||||
"model": MODEL_NAME,
|
||||
"queries": query,
|
||||
"documents": {"content": [documents[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
|
||||
@@ -1,9 +1,5 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
import base64
|
||||
|
||||
import requests
|
||||
|
||||
from vllm.entrypoints.utils import sanitize_message
|
||||
|
||||
|
||||
@@ -12,11 +8,3 @@ def test_sanitize_message():
|
||||
sanitize_message("<_io.BytesIO object at 0x7a95e299e750>")
|
||||
== "<_io.BytesIO object>"
|
||||
)
|
||||
|
||||
|
||||
def encode_base64_content_from_url(content_url: str) -> dict[str, str]:
|
||||
with requests.get(content_url) as response:
|
||||
response.raise_for_status()
|
||||
result = base64.b64encode(response.content).decode("utf-8")
|
||||
|
||||
return {"url": f"data:image/jpeg;base64,{result}"}
|
||||
|
||||
Reference in New Issue
Block a user