feat(modelopt): support real NVFP4 QAT rollout for MoE and Mamba

[HollowMan6]

Waiting for NVIDIA-NeMo/Megatron-Bridge#4566

What does this PR do ?

Add ModelOpt NVFP4 real-quant vLLM reload support for W4A16 fused-MoE rollout weights.

Issues

List issues that this PR closes (syntax):

• Resolves Support QAT for low precision RL #1750

Summary

• Add Nano3-specific real-quant ignore profile so Mamba, attention, gates/routers, shared experts, norms, and selected sensitive layers stay in BF16.
• Wire Megatron real-quant refit through export_hf_weights_modelopt(..., quant_mode="w4a16_nvfp4").
• Add Nano3 W4A16 real-quant recipe and nightly test entry.

Usage

Run the Nano3 W4A16 real-quant rollout recipe directly:

uv run --no-sync examples/run_grpo.py \
  --config examples/configs/recipes/llm/grpo-nanov3-30ba3b-4n4g-megatron-qa-nvfp4-w4a16-real.yaml

Or enable real-quant rollout on an existing Megatron + vLLM recipe:

policy:
  quant_cfg: examples/modelopt/quant_configs/nano3_nvfp4_weightonly.yaml
  generation:
    backend: vllm
    quant_cfg: examples/modelopt/quant_configs/nano3_nvfp4_weightonly.yaml
    real_quant: true
    real_quant_ignore: NANO3_NVFP4_IGNORE
    vllm_cfg:
      gpu_memory_utilization: 0.35
      enable_prefix_caching: false

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.