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

172
tests/v1/distributed/test_external_lb_dp.py
View File

@@ -26,12 +26,14 @@ class ExternalLBServerManager:
"""Manages data parallel vLLM server instances for external
load balancer testing."""
def __init__(self,
model_name: str,
dp_size: int,
api_server_count: int,
base_server_args: list,
tp_size: int = TP_SIZE):
def __init__(
self,
model_name: str,
dp_size: int,
api_server_count: int,
base_server_args: list,
tp_size: int = TP_SIZE,
):
self.model_name = model_name
self.dp_size = dp_size
self.tp_size = tp_size
@@ -47,20 +49,22 @@ class ExternalLBServerManager:
server_args = self.base_server_args.copy()
# Add external LB specific arguments
server_args.extend([
"--data-parallel-size",
str(self.dp_size),
"--data-parallel-rank",
str(rank),
"--data-parallel-size-local",
"1",
"--tensor-parallel-size",
str(self.tp_size),
"--port",
str(8000 + rank), # Different port for each rank
"--api-server-count",
str(self.api_server_count),
])
server_args.extend(
[
"--data-parallel-size",
str(self.dp_size),
"--data-parallel-rank",
str(rank),
"--data-parallel-size-local",
"1",
"--tensor-parallel-size",
str(self.tp_size),
"--port",
str(8000 + rank), # Different port for each rank
"--api-server-count",
str(self.api_server_count),
]
)
# Use a thread to start each server to allow parallel initialization
def start_server(r: int, sargs: list[str]):
@@ -71,25 +75,24 @@ class ExternalLBServerManager:
sargs,
auto_port=False,
env_dict={
"VLLM_SERVER_DEV_MODE":
"1",
current_platform.device_control_env_var:
",".join(
str(
current_platform.
device_id_to_physical_device_id(i))
for i in range(r * TP_SIZE, (r + 1) * TP_SIZE))
})
"VLLM_SERVER_DEV_MODE": "1",
current_platform.device_control_env_var: ",".join(
str(current_platform.device_id_to_physical_device_id(i))
for i in range(r * TP_SIZE, (r + 1) * TP_SIZE)
),
},
)
server.__enter__()
print(f"Server rank {r} started successfully with "
f"{self.api_server_count} API servers")
print(
f"Server rank {r} started successfully with "
f"{self.api_server_count} API servers"
)
self.servers.append((server, sargs))
except Exception as e:
print(f"Failed to start server rank {r}: {e}")
raise
thread = threading.Thread(target=start_server,
args=(rank, server_args))
thread = threading.Thread(target=start_server, args=(rank, server_args))
thread.start()
self.server_threads.append(thread)
@@ -132,9 +135,9 @@ def default_server_args():
@pytest.fixture(scope="module", params=[1, 4])
def server_manager(request, default_server_args):
api_server_count = request.param
server_manager = ExternalLBServerManager(MODEL_NAME, DP_SIZE,
api_server_count,
default_server_args)
server_manager = ExternalLBServerManager(
MODEL_NAME, DP_SIZE, api_server_count, default_server_args
)
with server_manager:
yield server_manager
@@ -174,18 +177,16 @@ def test_external_lb_server_info(server_manager):
# `n_reqs` is set so that there is a good chance each server
# receives at least one request
n_reqs = 2 * api_server_count * api_server_count
parallel_configs = [
_get_parallel_config(server) for _ in range(n_reqs)
]
api_process_counts = [
c["_api_process_count"] for c in parallel_configs
]
parallel_configs = [_get_parallel_config(server) for _ in range(n_reqs)]
api_process_counts = [c["_api_process_count"] for c in parallel_configs]
api_process_ranks = [c["_api_process_rank"] for c in parallel_configs]
assert all(c == api_server_count
for c in api_process_counts), api_process_counts
assert all(0 <= r < api_server_count
for r in api_process_ranks), api_process_ranks
assert all(c == api_server_count for c in api_process_counts), (
api_process_counts
)
assert all(0 <= r < api_server_count for r in api_process_ranks), (
api_process_ranks
)
@pytest.mark.asyncio
@@ -193,16 +194,15 @@ def test_external_lb_server_info(server_manager):
"model_name",
[MODEL_NAME],
)
async def test_external_lb_single_completion(clients: list[
openai.AsyncOpenAI], servers: list[tuple[RemoteOpenAIServer, list[str]]],
model_name: str) -> None:
async def test_external_lb_single_completion(
clients: list[openai.AsyncOpenAI],
servers: list[tuple[RemoteOpenAIServer, list[str]]],
model_name: str,
) -> None:
async def make_request(client: openai.AsyncOpenAI):
completion = await client.completions.create(
model=model_name,
prompt="Hello, my name is",
max_tokens=10,
temperature=1.0)
model=model_name, prompt="Hello, my name is", max_tokens=10, temperature=1.0
)
assert completion.id is not None
assert completion.choices is not None and len(completion.choices) == 1
@@ -256,11 +256,14 @@ async def test_external_lb_single_completion(clients: list[
_, server_args = servers[0]
api_server_count = (
server_args.count('--api-server-count')
and server_args[server_args.index('--api-server-count') + 1] or 1)
server_args.count("--api-server-count")
and server_args[server_args.index("--api-server-count") + 1]
or 1
)
print(
f"Successfully completed external LB test with {len(clients)} servers "
f"(API server count: {api_server_count})")
f"(API server count: {api_server_count})"
)
@pytest.mark.asyncio
@@ -268,9 +271,11 @@ async def test_external_lb_single_completion(clients: list[
"model_name",
[MODEL_NAME],
)
async def test_external_lb_completion_streaming(clients: list[
openai.AsyncOpenAI], servers: list[tuple[RemoteOpenAIServer, list[str]]],
model_name: str) -> None:
async def test_external_lb_completion_streaming(
clients: list[openai.AsyncOpenAI],
servers: list[tuple[RemoteOpenAIServer, list[str]]],
model_name: str,
) -> None:
prompt = "What is an LLM?"
async def make_streaming_request(client: openai.AsyncOpenAI):
@@ -284,11 +289,9 @@ async def test_external_lb_completion_streaming(clients: list[
single_output = single_completion.choices[0].text
# Perform the streaming request
stream = await client.completions.create(model=model_name,
prompt=prompt,
max_tokens=5,
temperature=0.0,
stream=True)
stream = await client.completions.create(
model=model_name, prompt=prompt, max_tokens=5, temperature=0.0, stream=True
)
chunks: list[str] = []
finish_reason_count = 0
last_chunk = None
@@ -299,16 +302,15 @@ async def test_external_lb_completion_streaming(clients: list[
last_chunk = chunk # Keep track of the last chunk
# finish reason should only return in the last block for OpenAI API
assert finish_reason_count == 1, (
"Finish reason should appear exactly once.")
assert last_chunk is not None, (
"Stream should have yielded at least one chunk.")
assert last_chunk.choices[
0].finish_reason == "length", "Finish reason should be 'length'."
assert finish_reason_count == 1, "Finish reason should appear exactly once."
assert last_chunk is not None, "Stream should have yielded at least one chunk."
assert last_chunk.choices[0].finish_reason == "length", (
"Finish reason should be 'length'."
)
# Check that the combined text matches the non-streamed version.
assert "".join(
chunks
) == single_output, "Streamed output should match non-streamed output."
assert "".join(chunks) == single_output, (
"Streamed output should match non-streamed output."
)
return True # Indicate success for this request
# Test single request to each server
@@ -324,10 +326,7 @@ async def test_external_lb_completion_streaming(clients: list[
all_tasks = []
for i, client in enumerate(clients):
tasks = [
make_streaming_request(client)
for _ in range(num_requests_per_server)
]
tasks = [make_streaming_request(client) for _ in range(num_requests_per_server)]
all_tasks.extend(tasks)
results = await asyncio.gather(*all_tasks)
@@ -339,10 +338,7 @@ async def test_external_lb_completion_streaming(clients: list[
# Second burst of streaming requests
all_tasks = []
for i, client in enumerate(clients):
tasks = [
make_streaming_request(client)
for _ in range(num_requests_per_server)
]
tasks = [make_streaming_request(client) for _ in range(num_requests_per_server)]
all_tasks.extend(tasks)
results = await asyncio.gather(*all_tasks)
@@ -351,7 +347,11 @@ async def test_external_lb_completion_streaming(clients: list[
_, server_args = servers[0]
api_server_count = (
server_args.count('--api-server-count')
and server_args[server_args.index('--api-server-count') + 1] or 1)
print(f"Successfully completed external LB streaming test with "
f"{len(clients)} servers (API server count: {api_server_count})")
server_args.count("--api-server-count")
and server_args[server_args.index("--api-server-count") + 1]
or 1
)
print(
f"Successfully completed external LB streaming test with "
f"{len(clients)} servers (API server count: {api_server_count})"
)