QuantizedEmbeddingBag¶

class aimet_torch.nn.QuantizedEmbeddingBag(*args, **kwargs)[source]¶

Quantized subclass of torch.nn.EmbeddingBag

forward(self, input: torch.Tensor, offsets: torch.Tensor | None = None, per_sample_weights: torch.Tensor | None = None) → torch.Tensor

Quantized forward of torch.nn.EmbeddingBag.

The input(s), parameter(s) (if any), and output(s) will be quantized with self.input_quantizers, self.param_quantizers, and self.output_quantizers respectively.

For more information, see QuantizationMixin.