Add Nemotron to PP_SUPPORTED_MODELS

[mgoin]

Followup to #6611 (comment)

Tested TP=2 + PP=2 with server:

vllm serve nvidia/Minitron-4B-Base --tensor-parallel-size 2 --pipeline-parallel-size 2

Client request and result:

curl http://0.0.0.0:8000/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer OPENAI_API_KEY" \
  -d '{
    "model": "nvidia/Minitron-4B-Base",
    "prompt": "The capital of the USA is" 
  }'
 
{"id":"cmpl-7029ed6cf71347c999a01361418bc6e2","object":"text_completion","created":1722094724,"model":"nvidia/Minitron-4B-Base","choices":[{"index":0,"text":" Washington D. C. which is a Fictional World. It was first mentioned in","logprobs":null,"finish_reason":"length","stop_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":22,"completion_tokens":16}}%  

[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 consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

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

🚀

[mgoin]

/ready

[youkaichao]

you can test the correctness locally with https://github.com/vllm-project/vllm/blob/main/tests/distributed/test_pipeline_parallel.py

[mgoin]

Thanks @youkaichao, all tests pass replacing Minitron for Llama