CLP解决了多Token预测加速中质量下降的核心痛点，做LLM推理优化的团队可以直接参考其轻量设计，在保持输出质量的同时获得稳定加速。
CLP提出了一种新的多Token预测（MTP）加速方法，解决了现有MTP方法中“头-主干竞争”导致的质量下降问题。该方法通过“主干即架构”原则，让主干语言模型头始终生成第一个Token，MTP头只负责后续Token。CLP使用轻量级线性层（4.6K-7.7K参数）预测可安全接受的Token数量，在Qwen2.5模型上实现1.14x-1.29x加速，且质量零损失（重复率<0.02），优于传统门控网络方法。实验表明，较短的预测窗口（k=2）在大模型上可恢复24%的MTP头准确率，为未来加速研究提供了清晰路线图。
CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference
Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass. Multi-token prediction (MTP) offers a promising acceleration path, but existing approaches suffer from a fundamental architectural flaw: the MTP head for the first token competes with the backbone's own language model (LM) head, leading to severe quality degradation when predictions are accepted. We identify this head-backbone competition as the root cause of repetitive and incoherent outputs in prior MTP-based acceleration methods. To address this, we propose Backbone-as-Architect, a design principle where the backbone LM head always generates the first token, and MTP heads are responsible only for subsequent tokens. Building on this principle, we introduce CLP (Collocation-Length Predictor), a lightweight span-level decision layer that predicts how many additional tokens can be safely accepted at each decoding step. CLP uses only a single linear layer (4.6K--7.7K parameters), replacing the over-engineered 1M-parameter gate networks used in prior work. Experiments on Qwen2.5 models (0.5B, 1.5B, 7B) show that CLP achieves 1.20x--1.29x speedup on 1.5B and 1.14x--1.20x on 7B, with zero quality degradation (repetition ratio < 0.02), while gate-based approaches fail to accelerate (1.07x) or produce severely degraded outputs (repetition ratio > 0.5%). We further demonstrate that shorter prediction horizons (k=2) recover 24% higher MTP head accuracy on large models, establishing a scaling-aware design principle. We identify MTP head prediction accuracy as the binding constraint on acceleration and establish a clear roadmap for future improvements.