torchrec/distributed/batched_embedding_kernel.py [390:442]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                weights_precision=BatchedFusedEmbeddingBag.to_sparse_type(
                    config.data_type
                ),
                device=device,
                **fused_params,
            )
        )
        self._optim: EmbeddingFusedOptimizer = EmbeddingFusedOptimizer(
            config,
            self._emb_module,
            pg,
        )

        self.init_parameters()

    @staticmethod
    def to_sparse_type(data_type: DataType) -> SparseType:
        if data_type == DataType.FP32:
            return SparseType.FP32
        elif data_type == DataType.FP16:
            return SparseType.FP16
        elif data_type == DataType.INT8:
            return SparseType.INT8
        else:
            raise ValueError(f"Invalid DataType {data_type}")

    @property
    def emb_module(
        self,
    ) -> SplitTableBatchedEmbeddingBagsCodegen:
        return self._emb_module

    @property
    def fused_optimizer(self) -> FusedOptimizer:
        return self._optim

    def named_parameters(
        self, prefix: str = "", recurse: bool = True
    ) -> Iterator[Tuple[str, nn.Parameter]]:
        yield from ()

    def named_buffers(
        self, prefix: str = "", recurse: bool = True
    ) -> Iterator[Tuple[str, torch.Tensor]]:
        for config, param in zip(
            self._config.embedding_tables,
            self.emb_module.split_embedding_weights(),
        ):
            key = append_prefix(prefix, f"{config.name}.weight")
            yield key, param

    def flush(self) -> None:
        self._emb_module.flush()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



torchrec/distributed/batched_embedding_kernel.py [644:696]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                weights_precision=BatchedFusedEmbeddingBag.to_sparse_type(
                    config.data_type
                ),
                device=device,
                **fused_params,
            )
        )
        self._optim: EmbeddingFusedOptimizer = EmbeddingFusedOptimizer(
            config,
            self._emb_module,
            pg,
        )

        self.init_parameters()

    @staticmethod
    def to_sparse_type(data_type: DataType) -> SparseType:
        if data_type == DataType.FP32:
            return SparseType.FP32
        elif data_type == DataType.FP16:
            return SparseType.FP16
        elif data_type == DataType.INT8:
            return SparseType.INT8
        else:
            raise ValueError(f"Invalid DataType {data_type}")

    @property
    def emb_module(
        self,
    ) -> SplitTableBatchedEmbeddingBagsCodegen:
        return self._emb_module

    @property
    def fused_optimizer(self) -> FusedOptimizer:
        return self._optim

    def named_parameters(
        self, prefix: str = "", recurse: bool = True
    ) -> Iterator[Tuple[str, nn.Parameter]]:
        yield from ()

    def named_buffers(
        self, prefix: str = "", recurse: bool = True
    ) -> Iterator[Tuple[str, torch.Tensor]]:
        for config, param in zip(
            self._config.embedding_tables,
            self.emb_module.split_embedding_weights(),
        ):
            key = append_prefix(prefix, f"{config.name}.weight")
            yield key, param

    def flush(self) -> None:
        self._emb_module.flush()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -