相关论文: CopySpec: Accelerating LLMs with Speculative Copy-…

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

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…

The immense model sizes of large language models (LLMs) challenge deployment on memory-limited consumer GPUs. Although model compression and parameter offloading are common strategies to address memory limitations, compression can degrade…

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleration. Many endeavors to…

Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effective tool use increasingly involves multi-step, multi-turn…

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to…

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large Reasoning Models (LRMs), which generate lengthy chains of…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full…

While Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to generate contextually grounded responses, contextual faithfulness remains challenging as LLMs may not consistently trust provided context, leading to…

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the…

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…