Are community contributions welcome?

[NancyFyong]

Hi, we've been reading through Molt for the past few days — really like how thin the RL loop is kept, and the fully-async agentic design.

Quick question before we start sending anything: are community PRs welcome at this stage, or is the repo mostly internal for now? I saw CONTRIBUTING.md and the DCO sign-off requirement, but wasn't sure whether that's meant for external contributors yet.

For context, I've upstreamed RL / diffusion work to a few related projects:

• https://github.com/verl-project/verl-omni
• https://github.com/Tencent-Hunyuan/UniRL
• https://github.com/modelscope/DiffSynth-Studio

Happy to start small (docs, tests, small fixes) if that's easier on your side. Thanks!

[hijkzzz]

Sure! Welcome to contribute.

[NancyFyong]

Sure! Welcome to contribute.

Thanks! I'd like to add LoRA / PEFT support to Molt. Rather than opening a PR directly,
I'll write an RFC first — the weight-sync design has a couple of reasonable options, and
I'd prefer to settle that with you up front.

Why I think this is a small change

• AutoModel already does the hard part: from_pretrained(..., peft_config=...) injects
  the adapters before sharding, and expert LoRA is EP-aware.
• peft is already listed in requirements.txt, with nothing currently importing it.

The part that needs real work is refit. Under LoRA the base weights are frozen, so refit
has to either:

• materialize W0 + scale*BA, or
• switch to native vLLM LoRA.

Skipping the adapter tensors would push only the unchanged weights and leave the rollout
engine stuck on the initial policy. Forwarding them as-is fails the flush outright —
AutoWeightsLoader raises on names it has no parameter for.

What the RFC will cover

• Scope — RL + SFT
• Refit choice — merge on refit vs. native vLLM LoRA (broadcast adapters only)
• Checkpointing
• Failure modes — which combinations should fail loudly
• Test plan

Open questions (before I write it)

1. Is LoRA in scope for Molt, or was it deliberately left out?
2. Where would you like the RFC — a separate issue, or a comment on this thread?

[NancyFyong]

Sure! Welcome to contribute.

Thanks! I'd like to add LoRA / PEFT support to Molt. Rather than opening a PR directly, I'll write an RFC first — the weight-sync design has a couple of reasonable options, and I'd prefer to settle that with you up front.

Why I think this is a small change

• AutoModel already does the hard part: from_pretrained(..., peft_config=...) injects
  the adapters before sharding, and expert LoRA is EP-aware.
• peft is already listed in requirements.txt, with nothing currently importing it.

The part that needs real work is refit. Under LoRA the base weights are frozen, so refit has to either:

• materialize W0 + scale*BA, or
• switch to native vLLM LoRA.

Skipping the adapter tensors would push only the unchanged weights and leave the rollout engine stuck on the initial policy. Forwarding them as-is fails the flush outright — AutoWeightsLoader raises on names it has no parameter for.

What the RFC will cover

• Scope — RL + SFT
• Refit choice — merge on refit vs. native vLLM LoRA (broadcast adapters only)
• Checkpointing
• Failure modes — which combinations should fail loudly
• Test plan

Open questions (before I write it)

1. Is LoRA in scope for Molt, or was it deliberately left out?
2. Where would you like the RFC — a separate issue, or a comment on this thread?

@hijkzzz Hi! Would you be able to review this when you have time? Thanks a lot!