BASS: Batched Attention-optimized Speculative Sampling
원문 초록
Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges. This paper describes a system of batched speculative decoding that sets a new state of the art in multi-sequence generation latency and that demonstrates superior GPU utilization as well as quality of generations within a time budget. For example, for a 7.8B-size model on a single A100 GPU and with a batch size of 8, each sequence is generated at an average speed of 5.8ms per token, the overall throughput being 1.1K tokens per second. These results represent state-of-the-art latency and a 2.15X speed-up over optimized regular decoding. Within a time budget that regular decoding does not finish, our system is able to generate sequences with HumanEval Pass@First of 43% and Pass@All of 61%, far exceeding what's feasible with single-sequence speculative decoding. Our peak GPU utilization during decoding reaches as high as 15.8%, more than 3X the highest of that of regular decoding and around 10X of single-sequence speculative decoding.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
any4: Learned 4-bit Numeric Representation for LLMs
APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation
Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI
Relative Entropy Pathwise Policy Optimization
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)
토론
이 논문과 연결된 포럼 글이 아직 없습니다.