Create a TIMM-based featurizer model with appropriate configurations. Args: model_id: The TIMM model ID to load

Create test DataProto for update_policy method

Recursively performs a deep comparison between two Python objects. - Handles NaN values correctly (NaN == NaN evaluates to True). - Handl

Dump rollout/validation samples as JSONL.

Dump rollout/validation samples as JSONL.

Extract and verify the format of the point list from the answer string. A valid format is a JSON list of dictionaries, where each dictionary

fetch tensor in tp shards across mp_group

Returns: entropy: # (bs, response_len) log_probs: # (bs, response_len)

Get master addr and port for this worker group

Get rank-specific checkpoint path following Megatron's convention. Returns path like: base_path/mp_rank_{tp:02d}_{pp:03d}_{ep:03d}/ Args:

Context manager for safe session access with proper connection pooling. Yields: aiohttp.ClientSession: Session instance for makin

Helper function containing the loading hf model logic

Log samples to wandb as a table

Create a numpy index array ensuring each group has at least 2 samples.

Normalize answer expressions.

Prepares input for action prediction by adding necessary tokens

Creates labels tensor for action prediction if not provided

Helper to get action masks from labels

Process vision features with optional FiLM conditioning

Deduplicate consecutive image tokens in prompt_ids for Qwen2.5-VL, since vLLM will replicate the <|image_pad|> token by image_data. For examp

Retry with exponential backoff

Remove generation prompt IDs from input tensors if they are present at the end.

Resolve device according to policy described in the module docstring. Priority: 1) explicit argument 2) VERL_FORCE_DEVICE env

Run diffusion-based action prediction

Determine whether the build should be paused