Bastion is a budget‑aware speculative decoding framework that uses tree‑structured block diffusion drafting to improve the efficiency of language model inference. It dynamically builds query‑dependent trees, balancing draft quality with hardware constraints, and incorporates an acceptance surrogate, an online latency estimator, and an adaptive best‑first expansion to maximize speed without sacrificing model distribution. The method achieves up to a 6.61× speedup over standard autoregressive decoding and outperforms state‑of‑the‑art block‑diffusion baselines by 39% across various benchmarks and GPU architectures.
arXiv:2608.20375v1 Announce Type: new Abstract: Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree b...
Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal rather than conditioned on tokens selected along each draft path.
arXiv:2608. 13524v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel.
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.
arXiv:2608. 10362v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive target model decoding steps.
arXiv:2606. 00487v1 Announce Type: new Abstract: Using a diffusion model for parallel drafting is a promising approach for speculative decoding.
arXiv:2606. 03819v1 Announce Type: new Abstract: One-shot block drafters for speculative decoding generate the full draft in a single forward pass, achieving strong throughput by eliminating sequential token generation.
arXiv:2609.22098v1 Announce Type: new Abstract: Speculative decoding accelerates language-model inference by letting a cheap drafter propose tokens that the target model verifies in parallel. Recent...
arXiv:2609.37029v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context...
arXiv:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which foll...
arXiv:2602. 20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios.
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...