Is your feature request related to a problem? Please describe.
Support RL training for DSV4 Flash.
Automodel dependency: NVIDIA-NeMo/Automodel#2034
vLLM dependency: vllm-project/vllm#40760

Describe the solution you'd like
A clear and concise description of what you want to happen.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
related watch list zpqiu#8