Skip to content

Fix: Resolve critical bugs in vLLM Online and Offline inference #209

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix: Resolve critical bugs in vLLM Online and Offline inference #209

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 16 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,21 @@ uv pip install --pre vllm==0.10.1+gptoss \
vllm serve openai/gpt-oss-20b
```

In case if the above installation did not work, these will work for Online Inference
```
sudo add-apt-repository ppa:deadsnakes/ppa -y
sudo apt update
sudo apt install python3.12 python3.12-venv python3.12-dev -y
python3.12 --version
python3.12 -m venv .oss
source .oss/bin/activate
pip install -U uv
uv pip install vllm==0.10.2 --torch-backend=auto
# uv pip install openai-harmony # This is optional for Online Serve but required for offline serve
# main copmmand to start the Online Inference Server
vllm serve openai/gpt-oss-20b --async-scheduling
```

[Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)

Offline Serve Code:
Expand Down Expand Up @@ -150,7 +165,7 @@ sampling = SamplingParams(
)

outputs = llm.generate(
prompt_token_ids=[prefill_ids], # batch of size 1
[TokensPrompt(prompt_token_ids=prefill_ids)],
sampling_params=sampling,
Comment on lines 167 to 169
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Import TokensPrompt for new vLLM API

The offline inference example now calls llm.generate([TokensPrompt(prompt_token_ids=prefill_ids)], …) but the snippet still only imports LLM and SamplingParams. Because TokensPrompt is not imported (e.g., from vllm.inputs import TokensPrompt), anyone copying this updated code will hit a NameError before reaching generation. Consider adding the import alongside the other vLLM imports so the example runs as advertised.

Useful? React with 👍 / 👎.

)

Expand Down