Add Rollout Function

Required callable signature:

def generate_rollout(args, rollout_id, data_source, evaluation=False) -> RolloutFnTrainOutput | RolloutFnEvalOutput:
    ...

Return types are defined in slime/rollout/base_types.py.

Step 3: Implement Train and Eval Branches Explicitly

• For training (evaluation=False), return RolloutFnTrainOutput(samples=..., metrics=...)
• For evaluation (evaluation=True), return RolloutFnEvalOutput(data=..., metrics=...)

Minimal skeleton:

from slime.rollout.base_types import RolloutFnTrainOutput, RolloutFnEvalOutput


def generate_rollout(args, rollout_id, data_source, evaluation=False):
    if evaluation:
        result = {
            "custom_eval": {
                "rewards": [],
                "truncated": [],
                "samples": [],
            }
        }
        return RolloutFnEvalOutput(data=result)

    groups = data_source.get_samples(args.rollout_batch_size)
    # fill Sample fields needed by training: tokens/response_length/reward/status (+ loss_mask when needed)
    return RolloutFnTrainOutput(samples=groups)

Step 4: Keep Data Contract Compatible

For each generated sample, ensure required training fields are populated consistently with your objective:

• tokens
• response_length
• reward (or reward dict if your setup uses keyed rewards)
• status

If partial rollout or masking logic is involved, keep loss_mask semantics consistent with existing behavior.

Step 5: Wire Through Arguments

Set your function path via CLI:

--rollout-function-path slime.rollout.<your_rollout>.generate_rollout

The default and signature expectation are documented in:

• slime/utils/arguments.py
• docs/en/get_started/customization.md

Common Mistakes

• Returning raw Python lists/dicts with mismatched schema in custom path
• Implementing only training branch and forgetting evaluation branch
• Generating samples without required fields (tokens, response_length, reward, status)
• Using blocking-heavy logic in high-frequency rollout paths without batching/concurrency control

Reference Locations

• Default rollout: slime/rollout/sglang_rollout.py
• Simple custom example: slime/rollout/sft_rollout.py
• Output dataclasses: slime/rollout/base_types.py
• Wiring/loading: slime/ray/rollout.py
• Argument definition: slime/utils/arguments.py
• Customization docs: docs/en/get_started/customization.md