[Bugfix] #31 _make_sampler_output return expected SequenceOutput output_token: int

[tstescoTT]

change log

• Fixes [Bug]: vLLM openai api_server errors out when stream=True #31
• _make_sampler_output return expected SequenceOutput output_token: int

summary

_make_sampler_output makes sense to do the conversion because input (cached_step_outputs) is expected to be List[torch.Tensor] so further upstream would require other changes.

vllm/vllm/worker/tt_model_runner.py::TTModelRunner::_make_sampler_output -> SamplerOutput

vllm/vllm/model_executor/layers/sampler.py::SamplerOutput

outputs: List[CompletionSequenceGroupOutput]

vllm/vllm/sequence.py::CompletionSequenceGroupOutput

samples: List[SequenceOutput]

vllm/vllm/sequence.py::SequenceOutput

output_token: int

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀