The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2608. 01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memory-bound.
arXiv:2608.01651v2 Announce Type: replace-cross Abstract: Emerging LLMs increasingly interleave full attention with recurrent linear attention to reduce long-context serving costs. Tree speculative d...
The paper introduces AdaptiveSpec, a training‑free speculative decoding method that simultaneously adapts the per‑step verification rule and the draft‑tree shape using signals generated during decoding. It replaces the fixed token‑match rule with a margin‑based threshold and adjusts tree depth, width, and node count based on draft confidence and recent acceptance history, allowing the total draft count to vary. Experiments on SGLang show up to 56% throughput gains over EAGLE‑3 while maintaining 93% of lossless task accuracy on GSM8K, MATH‑500, and HumanEval across three models.
arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.
The paper investigates why speculative decoding (SD) performs better than expected on sparse mixture-of-experts (MoE) models. By evaluating 10 large MoE models, the authors find that recent fine‑grained models achieve higher speedups at low batch sizes, contrary to prior predictions of a concave speedup‑batch relationship. They attribute this to lower verification costs driven by temporal overlap of draft tokens and GPU execution dynamics, and develop a maximum‑entropy IPF framework that accurately predicts unique expert counts from routing overlap, closely matching real‑model behavior.
arXiv:2604. 09731v2 Announce Type: replace-cross Abstract: Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass.