optimum/neuron/models/inference/qwen2/modeling_qwen2.py [75:96]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        super().__init__(config, neuron_config)

        self.embed_tokens = ParallelEmbedding(
            config.vocab_size,
            config.hidden_size,
            config.pad_token_id,
            dtype=neuron_config.torch_dtype,
            shard_across_embedding=not neuron_config.vocab_parallel,
            sequence_parallel_enabled=False,
            pad=True,
            use_spmd_rank=neuron_config.vocab_parallel,
        )

        self.lm_head = ColumnParallelLinear(
            config.hidden_size,
            config.vocab_size,
            gather_output=not neuron_config.on_device_sampling,
            bias=False,
            pad=True,
        )

        self.layers = nn.ModuleList(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/neuron/models/inference/qwen3/modeling_qwen3.py [71:92]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        super().__init__(config, neuron_config)

        self.embed_tokens = ParallelEmbedding(
            config.vocab_size,
            config.hidden_size,
            config.pad_token_id,
            dtype=neuron_config.torch_dtype,
            shard_across_embedding=not neuron_config.vocab_parallel,
            sequence_parallel_enabled=False,
            pad=True,
            use_spmd_rank=neuron_config.vocab_parallel,
        )

        self.lm_head = ColumnParallelLinear(
            config.hidden_size,
            config.vocab_size,
            gather_output=not neuron_config.on_device_sampling,
            bias=False,
            pad=True,
        )

        self.layers = nn.ModuleList(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -