Set the value of an attribute. Check if the attr is mutable before setting the value.

broadcast tensor in tp shards across mp_group

broadcast tensor in tp shards across mp_group

broadcast tensor in tp shards across mp_group

broadcast tensor in tp shards across mp_group

Compute loss with optional sequence parallelism and remove padding features

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

fetch tensor in tp shards across mp_group

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

Load dataset from config data paths for the given split. Args: split: The dataset split to load Returns: The

Helper function containing the loading hf model logic

Log samples to wandb as a table

Log a table of validation samples to the configured logger (wandb or swanlab)

Normalize answer expressions.

Process the padded outputs from _run_agent_loop and combine them into a batch.

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

Validate the bounding box dimensions and aspect ratio.

Apply KL penalty to the token-level rewards. This function computes the KL divergence between the reference policy and current policy, then a

Reroute to the appropriate apply_rotary_pos_emb function depending on bshd (conventional) / thd (packed seq) format In Qwen2-VL, the sha

Get async server class. Args: rollout_backend: str, rollout backend type (alias), should be "vllm" or "sglang". rollout_backend_m

Performs bootstrap resampling to estimate statistics of metrics. This function uses bootstrap resampling to estimate the mean and standard d

Build the memory buffer given weight_buffer_meta Args: weight_buffer_meta: contains mapping from name to a dictionary containing shape an

Bulk offload group.

calculate rollout vs actor logprobs diff, for debugging purpose Args: data: DataProto the data batch to calculate

Calls the remote sandbox API to execute code with retry logic for Gateway Timeout, using increasing delay between retries. Logs internal call

Calls the remote search API to perform retrieval with retry logic for various errors, using increasing delay between retries. Logs internal

A helper method to check if the passed module's key name matches any of the exclude modules in the adapter_config. Adapted from https://githu

A helper method to check if the passed module's key name matches any of the target modules in the adapter_config. Adapted from https://github

Computes various metrics from a batch of data for PPO training. This function calculates metrics related to scores, rewards, advantages, ret

Compute rollout group metrics for each episode. Args: batch: A DataProto object containing batch data with episode information.

Compute per-score metrics for each trajectory.

Computes timing metrics for different processing stages in PPO training. This function calculates both raw timing metrics (in seconds) and p

Deprecated. Please use copy_to_local instead.

Create a sampler for the dataset. Arguments: data_config: The data config. dataset (Dataset): The dataset. Returns:

Create a dataset.

name: name of the parameter train_params: training parameters infer_params (Iterable[torch.Tensor]): a iterator towards list of parameter

Ensure the DataProto is divisible by size_divisor by padding if necessary. Args: data: (DataProto): the DataProto to check size_d

The keys of the environment variables that are used to configure the Worker.

Execute the tool. Args: instance_id: The instance id of the tool. parameters: The json string of the parameters of th

Execute a method on all workers asynchronously. Args: method_name: Name of the method to execute *args: Positional ar

Execute a method on rank zero worker asynchronously. Args: method_name: Name of the method to execute *args: Position

Extract the equation from the solution string.

The training loop of PPO. The driver process only need to call the compute functions of the worker group through RPC to const

Args: input_ids: input ids. shape (batch_size, seq_length) attention_mask: attention_mask. shape (batch_size, seq_le

Args: input_ids: input ids. shape (batch_size, seq_length) attention_mask: attention_mask. shape (batch_size, seq_le

We assume: - The model takes input: (input_ids, attention_mask, position_ids). No rmpad for the input - The communication sha

r""" Copy paste LLaMa's forward https://github.com/linkedin/Liger-Kernel/blob/main/src/liger_kernel/transformers/model/llama.py This func