[Bugfix] Fix default weight loading for scalars

[mgoin]

It is pretty easy to run into issues when loading scalar weights from checkpoints into parameters, since they can have no shape in some cases, resulting in errors like

  File "/home/mgoin/code/vllm/vllm/model_executor/model_loader/weight_utils.py", line 525, in default_weight_loader
    assert param.size() == loaded_weight.size(), (
AssertionError: Attempted to load weight (torch.Size([1])) into parameter (torch.Size([]))

I think it makes sense to detect and allow "broadcasting" in this special case for ease of use.

[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.

🚀

[comaniac]

LGTM. I've been faced to this several times...