Skip to content

[ez] Fix app/vllm response processing broken by change in policy #123

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
Sep 4, 2025
Merged

[ez] Fix app/vllm response processing broken by change in policy #123

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
25b4108
[ez] Fix app/vllm response processing broken by change in policy
Jack-Khuu Sep 4, 2025
441d9ae
Lint
Jack-Khuu Sep 4, 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
6 changes: 3 additions & 3 deletions apps/vllm/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

from forge.actors.policy import Policy, PolicyConfig, SamplingOverrides, WorkerConfig
from forge.controller.service import ServiceConfig, shutdown_service, spawn_service
from vllm.outputs import CompletionOutput
from vllm.outputs import RequestOutput


async def main():
Expand Down Expand Up @@ -89,11 +89,11 @@ async def run_vllm(service_config: ServiceConfig, config: PolicyConfig, prompt:

async with policy.session():
print("Requesting generation...")
responses: List[CompletionOutput] = await policy.generate.choose(prompt=prompt)
response_output: RequestOutput = await policy.generate.choose(prompt=prompt)

print("\nGeneration Results:")
print("=" * 80)
for batch, response in enumerate(responses):
for batch, response in enumerate(response_output.outputs):
print(f"Sample {batch + 1}:")
print(f"User: {prompt}")
print(f"Assistant: {response.text}")
Expand Down
Loading