def _make_param_hook()

in picotron/data_parallel/data_parallel.py [0:0]

• 12 lines of code
• 6 McCabe index (conditional complexity)

    def _make_param_hook(self, param: torch.nn.Parameter,bucket_manager: BucketManager):
        """
        Creates the a hook for each parameter to handle gradient accumulation and synchronization.
        """
        def param_hook(*unused):
            """
            The hook called after the gradient is ready. It performs the following:
            1. Accumulates the gradient into the main gradient.
            2. Adds a post-backward callback to wait for gradient synchronization completion.
            3. Marks the parameter as ready for synchronization.
            """
            if param.requires_grad:
                assert param.grad is not None
                param.main_grad.add_(param.grad.data) # accumulate the gradients
                param.grad = None
                
                # skip the gradient synchronization (gradient accumulation/PP micro batches)
                if self.require_backward_grad_sync:
                    # Add a callback to wait for gradient synchronization. Ensures the callback is added only once.
                    # Callback is executed after the backward pass. It should be added per backward pass.
                    if not self._post_backward_callback_set:
                        Variable._execution_engine.queue_callback(self._post_backward)
                        self._post_backward_callback_set = True
                        
                    # mark the parameter as ready for gradient synchronization. 
                    bucket_manager.mark_param_as_ready(param) 
        return param_hook