paper-with-me

Papers

Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression

2024-12-07 · Michael R. Metel, Boxing Chen, Mehdi Rezagholizadeh

Several works have developed eviction policies to remove key-value (KV) pairs from the KV cache for more efficient inference. The focus has been on compressing the KV cache after the input prompt has been processed for faster token generation. In settings with limited GPU memory, and when the input context is longer than the generation length, we show that by also compressing the KV cache during the input processing phase, larger batch sizes can be used resulting in significantly higher throughput while still maintaining the original model's accuracy.

📄 PDF Abstract BibTeX arXiv:2412.05693

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction

2022-10-19 · Muralidhar Andoorveedu, Zhanda Zhu, Bojian Zheng, Gennady Pekhimenko

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by th…

GPU

MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching

2025-03-12 · Tairan Xu, Leyang Xue, Zhan Lu, Adrian Jackson 외

This paper presents MoE-Gen, a high-throughput MoE inference system optimized for single-GPU execution. Existing inference systems rely on model-based or continuous batching strategies, originally designed for interactiv…

GPU

SSSD: Simply-Scalable Speculative Decoding

2024-11-08 · Michele Marzollo, Jiawei Zhuang, Niklas Roemer, Lorenz K. Müller 외

Over the past year, Speculative Decoding has gained popularity as a technique for accelerating Large Language Model inference. While several methods have been introduced, most struggle to deliver satisfactory performance…

Language ModelingLanguage ModellingLarge Language Model

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving

2025-12-27 · Rui Li, Zhaoning Zhang, Libo Zhang, Huaimin Wang 외 arxiv

Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades perform…

A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks

2017-02-20 · Yixing Li, Zichuan Liu, Kai Xu, Hao Yu 외

FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a h…

GPU