Related papers: Making Every Verified Token Count: Adaptive Verifi…
Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…
Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…
Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency…
Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However,…
Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…
Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…
Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that are subsequently verified by the target model. The…
Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…
Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…
Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify…
Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…
Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel. A common way to build draft models, like EAGLE3 or DFlash is supervised…
Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…
Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or…
We introduce an adaptive tree search algorithm, that can find high-scoring outputs under translation models that make no assumptions about the form or structure of the search objective. This algorithm -- a deterministic variant of Monte…
Speculative sampling reduces the latency of autoregressive decoding for target model LLMs without sacrificing inference quality, by using a cheap draft model to suggest a candidate token and a verification criterion to accept or resample…
Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…
The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by…
Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could…
Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference,…