research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPS
content type paperpublished November 2024

Speculative Streaming: Fast LLM Inference Without Auxiliary Models

AuthorsNikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi

View publication

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024.

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both draft and target models to achieve high acceptance rates. As the number of downstream tasks grows, these draft models add significant complexity to inference systems. We propose Speculative Streaming, a single-model speculative decoding method that fuses drafting into the target model by changing the fine-tuning objective from next token prediction to future n-gram prediction. Speculative Streaming speeds up decoding by 1.8 - 3.1X in a diverse set of tasks, such as Summarization, Structured Queries, and Meaning Representation, without sacrificing generation quality. Additionally, Speculative Streaming is parameter-efficient. It achieves on-par/higher speed-ups than Medusa-style architectures while using ~10000X fewer extra parameters, making it well-suited for resource-constrained devices.

Related readings and updates.

Accelerating LLM Inference on NVIDIA GPUs with ReDrafter

Accelerating LLM inference is an important ML research problem, as auto-regressive token generation is computationally expensive and relatively slow, and improving inference efficiency can reduce latency for users. In addition to ongoing efforts to accelerate inference on Apple silicon, we have recently made significant progress in accelerating LLM inference for the NVIDIA GPUs widely used for production applications across the industry. Earlier…
See highlight details

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent neural network (RNN) as the draft model conditioning on LLM's hidden states, (2) applying a dynamic tree attention algorithm over beam search results to eliminate duplicated prefixes in candidate…
See paper details