Skip to content

mark vLLM policy integration tests as async #416

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 15, 2025
Merged

mark vLLM policy integration tests as async #416

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4058b4f
mark vLLM policy integration tests as async
ebsmothers Oct 14, 2025
a504c46
comments
ebsmothers Oct 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 5 additions & 13 deletions tests/integration_tests/test_vllm_policy_correctness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.

import asyncio
import pytest

from forge.actors.policy import Policy
from vllm import SamplingParams
Expand All @@ -28,6 +28,7 @@
N_SAMPLES = 1


@pytest.mark.asyncio
async def test_same_output():
"""Compare outputs between vLLM and Policy service"""
test_prompts = [
Expand Down Expand Up @@ -96,15 +97,14 @@ async def test_same_output():
for vllm_output, policy_output in zip(vllm_outputs, policy_outputs):
assert vllm_output != ""
assert policy_output != ""
if vllm_output != policy_output:
print(f"❌ Got different results: {vllm_output} vs. {policy_output}")
print("✅ Outputs are the same!")
assert vllm_output == policy_output

finally:
if policy is not None:
await policy.shutdown()


@pytest.mark.asyncio
async def test_cache_usage():
"""Test that KV cache usage is consistent between vLLM and Policy service.
Expand Down Expand Up @@ -232,16 +232,8 @@ async def test_cache_usage():
for vllm_output, policy_output in zip(vllm_outputs, policy_outputs):
assert vllm_output != ""
assert policy_output != ""
if vllm_output != policy_output:
print(f"❌ Got different results: {vllm_output} vs. {policy_output}")

print("\n✅ Prefix cache usage is the same!")
assert vllm_output == policy_output

finally:
if policy is not None:
await policy.shutdown()


if __name__ == "__main__":
asyncio.run(test_same_output())
asyncio.run(test_cache_usage())
Loading