verl/utils/megatron/memory.py

# Copyright 2024 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import torch


class MemoryBuffer:
    def __init__(self, numel, numel_padded, dtype):
        self.numel = numel
        self.numel_padded = numel_padded
        self.dtype = dtype
        self.data = torch.zeros(self.numel_padded, dtype=self.dtype, device=torch.cuda.current_device(), requires_grad=False)

    def zero(self):
        """Reset the buffer to zero."""
        self.data.zero_()

    def get(self, shape, start_index):
        """Return a tensor with the input `shape` as a view into the
        1-D data starting at `start_index`."""
        end_index = start_index + shape.numel()
        assert end_index <= self.numel, "requested tensor is out of the buffer range."
        buffer_tensor = self.data[start_index:end_index]
        buffer_tensor = buffer_tensor.view(shape)
        return buffer_tensor