paper-with-me

Papers

TENSILE: A Tensor granularity dynamic GPU memory scheduling method toward multiple dynamic workloads system

2021-05-27 · Kaixin Zhang, Hongzhi Wang, Han Hu, Songling Zou, Jiye Qiu, Tongxin Li, Zhishun Wang

Recently, deep learning has been an area of intense research. However, as a kind of computing-intensive task, deep learning highly relies on the scale of GPU memory, which is usually prohibitive and scarce. Although some extensive works have been proposed for dynamic GPU memory management, they are hard to apply to systems with multiple dynamic workloads, such as in-database machine learning systems. In this paper, we demonstrated TENSILE, a method of managing GPU memory in tensor granularity to reduce the GPU memory peak, considering the multiple dynamic workloads. TENSILE tackled the cold-starting and across-iteration scheduling problem existing in previous works. We implemented TENSILE on a deep learning framework built by ourselves and evaluated its performance. The experiment results show that TENSILE can save more GPU memory with less extra overhead than prior works in single and multiple dynamic workloads scenarios.

📄 PDF Abstract BibTeX arXiv:2105.13336

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGPUManagementScheduling

Similar Papers 제목 키워드 기반

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing

2024-07-12 · Husheng Han, Xinyao Zheng, Yuanbo Wen, Yifan Hao 외

Heterogeneous collaborative computing with NPU and CPU has received widespread attention due to its substantial performance benefits. To ensure data confidentiality and integrity during computing, Trusted Execution Envir…

CPULanguage ModellingLarge Language ModelScheduling

Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

2026-07-11 · Yangyijian Liu, Hongyi Ye, Mingyang Li, Wu-jun Li arxiv

Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capaci…

TimeRL: Efficient Deep Reinforcement Learning with Polyhedral Dependence Graphs

2025-01-09 · Pedro F. Silvestre, Peter Pietzuch

Modern deep learning (DL) workloads increasingly use complex deep reinforcement learning (DRL) algorithms that generate training data within the learning loop. This results in programs with several nested loops and dynam…

CPUDeep Reinforcement LearningGPUreinforcement-learning+2

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

2026-03-29 · Songchen Ma, Hongyi Li, Weihao Zhang, Yonghao Tan 외 arxiv

Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs …

Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs

2022-10-18 · Yaoyao Ding, Cody Hao Yu, Bojian Zheng, Yizhi Liu 외

As deep learning models nowadays are widely adopted by both cloud services and edge devices, reducing the latency of deep learning model inferences becomes crucial to provide efficient model serving. However, it is chall…

Deep LearningScheduling