bitsandbytes/autograd/_functions.py [429:456]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ctx.tensor_states = (None, None)
            ctx.save_for_backward(None, None)

        clone_func = torch.clone if len(output_shape) == 3 else lambda x: x
        return clone_func(output.view(output_shape))

    @staticmethod
    def backward(ctx, grad_output):
        if ctx.is_empty:
            bias_grad = None if ctx.bias is None else torch.zeros_like(ctx.bias)
            return torch.zeros_like(ctx.A), torch.zeros_like(ctx.B), None, bias_grad, None
        req_gradA, req_gradB, _, req_gradBias, _ = ctx.needs_input_grad
        CAt, subA, A = ctx.tensors
        SCAt, idx = ctx.tensor_states
        formatB = ctx.formatB
        state = ctx.state
        grad_A = grad_B = grad_bias = None

        if req_gradBias:
            # compute grad_bias first before changing grad_output dtype
            grad_bias = grad_output.sum(0, dtype=ctx.dtype_bias)

        # Cast grad_output to fp16
        if len(grad_output.shape) == 3:
            grad_output = grad_output.reshape(-1, grad_output.shape[-1]).contiguous()

        Cgrad, Cgradt, SCgrad, SCgradt, coo_tensor = F.double_quant(grad_output.to(torch.float16))
        if req_gradB:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



bitsandbytes/research/autograd/_functions.py [313:341]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ctx.tensor_states = (None, None)
            ctx.save_for_backward(None, None)

        clone_func = torch.clone if len(output_shape) == 3 else lambda x: x
        return clone_func(output.view(output_shape))

    @staticmethod
    def backward(ctx, grad_output):
        if ctx.is_empty:
            bias_grad = None if ctx.bias is None else torch.zeros_like(ctx.bias)
            return torch.zeros_like(ctx.A), torch.zeros_like(ctx.B), None, bias_grad, None
        req_gradA, req_gradB, _, req_gradBias, _ = ctx.needs_input_grad
        CAt, subA, A = ctx.tensors
        SCAt, idx = ctx.tensor_states
        formatB = ctx.formatB
        state = ctx.state
        grad_A = grad_B = grad_bias = None

        if req_gradBias:
            # compute grad_bias first before changing grad_output dtype
            grad_bias = grad_output.sum(0, dtype=ctx.dtype_bias)

        # Cast grad_output to fp16
        if len(grad_output.shape) == 3:
            grad_output = grad_output.reshape(-1, grad_output.shape[-1]).contiguous()

        Cgrad, Cgradt, SCgrad, SCgradt, coo_tensor = F.double_quant(grad_output.to(torch.float16))

        if req_gradB:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -