Support direct weight loading

[fzyzcjy]

Motivation

Just #2845

This PR supports verl megatron weights to be passed in.

Modifications

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

[FrankLeeeee]

Can you explain your PR a bit including the motivation and implementation?

[fzyzcjy]

@FrankLeeeee Hi, this is one PR among the series to integrate SGLang into Verl, and is being reviewed now. After the dependent PRs are merged, the code diff shown in github will be much cleaner.

[FrankLeeeee]

@FrankLeeeee Hi, this is one PR among the series to integrate SGLang into Verl, and is being reviewed now. After the dependent PRs are merged, the code diff shown in github will be much cleaner.

Noted, thanks!

[fzyzcjy]

You are welcome!

[fzyzcjy]

After discussing with Lianmin, now I know there is no need to follow implementation requirements in e.g. 2736. Thus I spent several hours writing a new PR #3852, and this one is deprecated.