arctic_inference/vllm/spec_dec/arctic_speculator.py [156:164]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                bias=False,
                quant_config=quant_config,
                skip_quantization=True,
            )
            self.head = nn.ModuleList([head] * self.max_speculative_tokens)

            if self.quantize_lm_head:
                qhead = ParallelLMHead(
                    self.vocab_size,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



arctic_inference/vllm/spec_dec/arctic_speculator.py [448:456]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                bias=False,
                quant_config=quant_config,
                skip_quantization=True,
            )
            self.head = nn.ModuleList([head] * self.max_speculative_tokens)

            if self.quantize_lm_head:
                qhead = ParallelLMHead(
                    self.vocab_size,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -