arctic_inference/vllm/spec_dec/vocab_parallel_embedding.py [223:228]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                 params_dtype: Optional[torch.dtype] = None,
                 org_num_embeddings: Optional[int] = None,
                 padding_size: int = DEFAULT_VOCAB_PADDING_SIZE,
                 quant_config: Optional[QuantizationConfig] = None,
                 prefix: str = "",
                 skip_quantization: bool = True):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



arctic_inference/vllm/spec_dec/vocab_parallel_embedding.py [475:480]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                 params_dtype: Optional[torch.dtype] = None,
                 org_num_embeddings: Optional[int] = None,
                 padding_size: int = DEFAULT_VOCAB_PADDING_SIZE,
                 quant_config: Optional[QuantizationConfig] = None,
                 prefix: str = "",
                 skip_quantization: bool = True):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -