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

[V0 Deprecation] Remove pooling model support in V0 (#23434)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Maximilien de Bayser
2025-08-29 04:04:02 -03:00
committed by GitHub
parent 934bebf192
commit 2554b27baa
38 changed files with 99 additions and 808 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/entrypoints/openai/test_embedding.py
View File

@@ -24,14 +24,6 @@ DUMMY_CHAT_TEMPLATE = """{% for message in messages %}{{message['role'] + ': ' +
DTYPE = "bfloat16"
@pytest.fixture(autouse=True)
def v1(run_with_both_engines):
# Simple autouse wrapper to run both engines for each test
# This can be promoted up to conftest.py to run for every
# test in a package
pass
@pytest.fixture(scope="module")
def server():
args = [

8
tests/entrypoints/openai/test_rerank.py
View File

@@ -14,14 +14,6 @@ MODEL_NAME = "BAAI/bge-reranker-base"
DTYPE = "bfloat16"
@pytest.fixture(autouse=True)
def v1(run_with_both_engines):
# Simple autouse wrapper to run both engines for each test
# This can be promoted up to conftest.py to run for every
# test in a package
pass
@pytest.fixture(scope="module")
def server():
args = ["--enforce-eager", "--max-model-len", "100", "--dtype", DTYPE]

9
tests/entrypoints/openai/test_score.py
View File

@@ -12,15 +12,6 @@ from vllm.entrypoints.openai.protocol import ScoreResponse
from ...utils import RemoteOpenAIServer
@pytest.fixture(autouse=True)
def v1(run_with_both_engines):
# Simple autouse wrapper to run both engines for each test
# This can be promoted up to conftest.py to run for every
# test in a package
pass
MODELS = [
{
"name": "BAAI/bge-reranker-v2-m3",