def __init__()

in arctic_inference/vllm/swiftkv/llama_swiftkv.py [0:0]

• 26 lines of code
• 2 McCabe index (conditional complexity)

    def __init__(self,
                 *,
                 vllm_config: VllmConfig,
                 prefix: str = ""):
        super().__init__()
        config = vllm_config.model_config.hf_config
        quant_config = vllm_config.quant_config
        self.config = config

        self.model = self._init_model(vllm_config=vllm_config,
                                      prefix=maybe_prefix(prefix, "model"))

        self.unpadded_vocab_size = config.vocab_size

        self.lm_head = ParallelLMHead(
            self.unpadded_vocab_size,
            config.hidden_size,
            org_num_embeddings=config.vocab_size,
            padding_size=DEFAULT_VOCAB_PADDING_SIZE,
            quant_config=quant_config,
            prefix=maybe_prefix(prefix, "lm_head"),
        )
        if config.tie_word_embeddings:
            self.lm_head = self.lm_head.tie_weights(
                self.model.embed_tokens)

        logit_scale = getattr(config, "logit_scale", 1.0)
        self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
                                                config.vocab_size,
                                                logit_scale)