Related papers: BASS: Batched Attention-optimized Speculative Samp…

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying…

Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While speculative decoding has been explored to mitigate this…

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free…

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad…

Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propose draft tokens in advance, and validating them in parallel with the large target model. However,…

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing…

The goal of $L$-step speculative decoding is to accelerate autoregressive decoding of a target model by using a cheaper draft model to generate a candidate path of $L$ tokens. Based on a verification algorithm involving target and draft…

This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment. By conditioning draft predictions on both…

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…

Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a single parallel step. However, since these parallel predictions are sampled from…

In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU…

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even…

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, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

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…

The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic…

Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial latency. We introduce…