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

Convert formatting to use ruff instead of yapf + isort (#26247)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 15:06:22 +01:00
committed by GitHub
parent 17edd8a807
commit d6953beb91
1508 changed files with 115244 additions and 94146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
tests/entrypoints/pooling/openai/test_pooling.py
View File

@@ -46,11 +46,7 @@ async def test_single_pooling(server: RemoteOpenAIServer, model_name: str):
# test single pooling
response = requests.post(
server.url_for("pooling"),
json={
"model": model_name,
"input": input_texts,
"encoding_format": "float"
},
json={"model": model_name, "input": input_texts, "encoding_format": "float"},
)
response.raise_for_status()
poolings = PoolingResponse.model_validate(response.json())
@@ -66,11 +62,7 @@ async def test_single_pooling(server: RemoteOpenAIServer, model_name: str):
input_tokens = [1, 1, 1, 1, 1]
response = requests.post(
server.url_for("pooling"),
json={
"model": model_name,
"input": input_tokens,
"encoding_format": "float"
},
json={"model": model_name, "input": input_tokens, "encoding_format": "float"},
)
response.raise_for_status()
poolings = PoolingResponse.model_validate(response.json())
@@ -88,16 +80,13 @@ async def test_single_pooling(server: RemoteOpenAIServer, model_name: str):
async def test_batch_pooling(server: RemoteOpenAIServer, model_name: str):
# test list[str]
input_texts = [
"The cat sat on the mat.", "A feline was resting on a rug.",
"Stars twinkle brightly in the night sky."
"The cat sat on the mat.",
"A feline was resting on a rug.",
"Stars twinkle brightly in the night sky.",
]
response = requests.post(
server.url_for("pooling"),
json={
"model": model_name,
"input": input_texts,
"encoding_format": "float"
},
json={"model": model_name, "input": input_texts, "encoding_format": "float"},
)
response.raise_for_status()
poolings = PoolingResponse.model_validate(response.json())
@@ -110,15 +99,15 @@ async def test_batch_pooling(server: RemoteOpenAIServer, model_name: str):
assert poolings.usage.total_tokens == 29
# test list[list[int]]
input_tokens = [[4, 5, 7, 9, 20], [15, 29, 499], [24, 24, 24, 24, 24],
[25, 32, 64, 77]]
input_tokens = [
[4, 5, 7, 9, 20],
[15, 29, 499],
[24, 24, 24, 24, 24],
[25, 32, 64, 77],
]
response = requests.post(
server.url_for("pooling"),
json={
"model": model_name,
"input": input_tokens,
"encoding_format": "float"
},
json={"model": model_name, "input": input_tokens, "encoding_format": "float"},
)
response.raise_for_status()
poolings = PoolingResponse.model_validate(response.json())
@@ -133,18 +122,21 @@ async def test_batch_pooling(server: RemoteOpenAIServer, model_name: str):
@pytest.mark.asyncio
@pytest.mark.parametrize("model_name", [MODEL_NAME])
async def test_conversation_pooling(server: RemoteOpenAIServer,
model_name: str):
messages = [{
"role": "user",
"content": "The cat sat on the mat.",
}, {
"role": "assistant",
"content": "A feline was resting on a rug.",
}, {
"role": "user",
"content": "Stars twinkle brightly in the night sky.",
}]
async def test_conversation_pooling(server: RemoteOpenAIServer, model_name: str):
messages = [
{
"role": "user",
"content": "The cat sat on the mat.",
},
{
"role": "assistant",
"content": "A feline was resting on a rug.",
},
{
"role": "user",
"content": "Stars twinkle brightly in the night sky.",
},
]
chat_response = requests.post(
server.url_for("pooling"),
@@ -180,24 +172,22 @@ async def test_conversation_pooling(server: RemoteOpenAIServer,
},
)
completions_response.raise_for_status()
completion_poolings = PoolingResponse.model_validate(
completions_response.json())
completion_poolings = PoolingResponse.model_validate(completions_response.json())
assert chat_poolings.id is not None
assert completion_poolings.id is not None
assert chat_poolings.created <= completion_poolings.created
assert chat_poolings.model_dump(
exclude={"id", "created"}) == (completion_poolings.model_dump(
exclude={"id", "created"}))
assert chat_poolings.model_dump(exclude={"id", "created"}) == (
completion_poolings.model_dump(exclude={"id", "created"})
)
@pytest.mark.asyncio
@pytest.mark.parametrize("model_name", [MODEL_NAME])
async def test_batch_base64_pooling(server: RemoteOpenAIServer,
model_name: str):
async def test_batch_base64_pooling(server: RemoteOpenAIServer, model_name: str):
input_texts = [
"Hello my name is",
"The best thing about vLLM is that it supports many different models"
"The best thing about vLLM is that it supports many different models",
]
float_response = requests.post(
@@ -210,9 +200,7 @@ async def test_batch_base64_pooling(server: RemoteOpenAIServer,
)
float_response.raise_for_status()
responses_float = PoolingResponse.model_validate(float_response.json())
float_data = [
np.array(d.data).squeeze(-1).tolist() for d in responses_float.data
]
float_data = [np.array(d.data).squeeze(-1).tolist() for d in responses_float.data]
base64_response = requests.post(
server.url_for("pooling"),
@@ -228,13 +216,15 @@ async def test_batch_base64_pooling(server: RemoteOpenAIServer,
decoded_responses_base64_data = []
for data in responses_base64.data:
decoded_responses_base64_data.append(
np.frombuffer(base64.b64decode(data.data),
dtype="float32").tolist())
np.frombuffer(base64.b64decode(data.data), dtype="float32").tolist()
)
check_embeddings_close(embeddings_0_lst=float_data,
embeddings_1_lst=decoded_responses_base64_data,
name_0="float32",
name_1="base64")
check_embeddings_close(
embeddings_0_lst=float_data,
embeddings_1_lst=decoded_responses_base64_data,
name_0="float32",
name_1="base64",
)
# Default response is float32 decoded from base64 by OpenAI Client
default_response = requests.post(
@@ -250,10 +240,12 @@ async def test_batch_base64_pooling(server: RemoteOpenAIServer,
np.array(d.data).squeeze(-1).tolist() for d in responses_default.data
]
check_embeddings_close(embeddings_0_lst=float_data,
embeddings_1_lst=default_data,
name_0="float32",
name_1="default")
check_embeddings_close(
embeddings_0_lst=float_data,
embeddings_1_lst=default_data,
name_0="float32",
name_1="default",
)
@pytest.mark.asyncio
@@ -268,39 +260,46 @@ async def test_invocations(server: RemoteOpenAIServer):
"encoding_format": "float",
}
completion_response = requests.post(server.url_for("pooling"),
json=request_args)
completion_response = requests.post(server.url_for("pooling"), json=request_args)
completion_response.raise_for_status()
invocation_response = requests.post(server.url_for("invocations"),
json=request_args)
invocation_response = requests.post(
server.url_for("invocations"), json=request_args
)
invocation_response.raise_for_status()
completion_output = completion_response.json()
invocation_output = invocation_response.json()
assert completion_output.keys() == invocation_output.keys()
for completion_data, invocation_data in zip(completion_output["data"],
invocation_output["data"]):
for completion_data, invocation_data in zip(
completion_output["data"], invocation_output["data"]
):
assert completion_data.keys() == invocation_data.keys()
check_embeddings_close(embeddings_0_lst=completion_data["data"],
embeddings_1_lst=invocation_data["data"],
name_0="completion",
name_1="invocation")
check_embeddings_close(
embeddings_0_lst=completion_data["data"],
embeddings_1_lst=invocation_data["data"],
name_0="completion",
name_1="invocation",
)
@pytest.mark.asyncio
async def test_invocations_conversation(server: RemoteOpenAIServer):
messages = [{
"role": "user",
"content": "The cat sat on the mat.",
}, {
"role": "assistant",
"content": "A feline was resting on a rug.",
}, {
"role": "user",
"content": "Stars twinkle brightly in the night sky.",
}]
messages = [
{
"role": "user",
"content": "The cat sat on the mat.",
},
{
"role": "assistant",
"content": "A feline was resting on a rug.",
},
{
"role": "user",
"content": "Stars twinkle brightly in the night sky.",
},
]
request_args = {
"model": MODEL_NAME,
@@ -311,18 +310,22 @@ async def test_invocations_conversation(server: RemoteOpenAIServer):
chat_response = requests.post(server.url_for("pooling"), json=request_args)
chat_response.raise_for_status()
invocation_response = requests.post(server.url_for("invocations"),
json=request_args)
invocation_response = requests.post(
server.url_for("invocations"), json=request_args
)
invocation_response.raise_for_status()
chat_output = chat_response.json()
invocation_output = invocation_response.json()
assert chat_output.keys() == invocation_output.keys()
for chat_data, invocation_data in zip(chat_output["data"],
invocation_output["data"]):
for chat_data, invocation_data in zip(
chat_output["data"], invocation_output["data"]
):
assert chat_data.keys() == invocation_data.keys()
check_embeddings_close(embeddings_0_lst=chat_data["data"],
embeddings_1_lst=invocation_data["data"],
name_0="chat",
name_1="invocation")
check_embeddings_close(
embeddings_0_lst=chat_data["data"],
embeddings_1_lst=invocation_data["data"],
name_0="chat",
name_1="invocation",
)