Related papers: SpecHop: Continuous Speculation for Accelerating M…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings,…

Real-time sequential control agents are often bottlenecked by inference latency. Even modest per-step planning delays can destabilize control and degrade overall performance. We propose a speculation-and-correction framework that adapts the…

Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert…

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While…

Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable…

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…

In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necessary for speculative sampling can be computed concurrently.…

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high…

Speculative Decoding promises to accelerate the inference of Large Language Models, yet its efficacy often degrades in production-grade serving. Existing evaluations typically overlook the compute-bound nature of high-concurrency regimes,…

Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previous methods either adopt a fixed speculative decoding…

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…

Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and…

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving complex mathematical and programming tasks. However, its efficiency is constrained by the…

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned tokens.…

Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose…

Research in automatic parallelization of loop-centric programs started with static analysis, then broadened its arsenal to include dynamic inspection-execution and speculative execution, the best results involving hybrid static-dynamic…