[BugFix] Fix sglang and vllm engine args

[ETOgaosion]

Checklist Before Starting

• Search for similar PR(s).

What does this PR do?

#1616 causes vllm engine arg init failed, not know why CI of that PR fail to detect. Some errors have shown up.

We may better separate engine args for different inference systems

High-Level Design

Demonstrate the high-level design if this PR is complex.

Specific Changes

List the specific changes.

API

    engine_kwargs: # inference engine parameters
      vllm:
        swap_space: null # null means "use the engine default value" (usually 4 GB), setting it to, e.g., 32 means 32 GB
      sglang:
        attention_backend: null # null means use the engine default value, available options: flashinfer, triton, flashmla

Usage Example

Provide usage example(s) for easier usage.

# Add code snippet or script demonstrating how to use this 

Test

For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluatuion results, etc.

Additional Info.

• Issue Number: Fixes issue # or discussion # if any.
• Training: [Note which backend this PR will affect: FSDP, Megatron, both, or none]
• Inference: [Note which backend this PR will affect: vLLM, SGLang, both, or none]

Checklist Before Submitting

• Read the Contribute Guide.
• Apply pre-commit checks.
• Add [BREAKING] to the PR title if it breaks any API.
• Update the documentation about your changes in the docs.
• Add CI test(s) if necessary.

[vermouth1992]

Shall we separate vllm and sglang config args from a higher level?

[ETOgaosion]

Shall we separate vllm and sglang config args from a higher level?

Seems that the only separate configuration of these two systems is the engine_kwargs, the abstraction is good.

[hebiao064]

Sorry for that, thanks for fixing it