相关论文: EAGLE-Pangu: Accelerator-Safe Tree Speculative Dec…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the…

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

Speculative decoding is a technique to leverage hardware concurrency in order to enable multiple steps of token generation in a single forward pass, thus improving the efficiency of large-scale autoregressive (AR) Transformer models.…

Cloud workloads have dominated generative AI based on large language models (LLM). Specialized hardware accelerators, such as GPUs, NPUs, and TPUs, play a key role in AI adoption due to their superior performance over general-purpose CPUs.…

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language…

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass. However, existing methods prioritize maximizing token-level likelihood or the number…

The auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. While recent research has investigated various speculative decoding techniques for multi-token generation, these…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the…

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the…

Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model…

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 is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face…

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…