Related papers: AdaEAGLE: Optimizing Speculative Decoding via Expl…

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…

Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…

End-to-end automatic speech recognition (ASR) systems based on transformer architectures, such as Whisper, offer high transcription accuracy and robustness. However, their autoregressive decoding is computationally expensive, hence limiting…

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In…

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However,…

Speculative decoding accelerates autoregressive language models by using a lightweight drafter to propose multiple future tokens, which the target model then verifies in parallel. DFlash shows that a block diffusion drafter can generate 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…

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

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…

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,…

Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a…

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this…

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…

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…