Zobrazeno 1 - 10
of 862
pro vyhledávání: '"LI Baolin"'
Publikováno v:
矿业科学学报, Vol 9, Iss 3, Pp 342-350 (2024)
This study conducted the CO2-PTF coal experiment to further reveal the fracturing transformation mechanism of CO2 phase transition fracturing(CO2-PTF)coal. According to the CT scanning and 3D fracture reconstruction, we analyzed the fracture structur
Externí odkaz:
https://doaj.org/article/18bef17af7664f86bf38f2f69371c353
This work introduces ECOLIFE, the first carbon-aware serverless function scheduler to co-optimize carbon footprint and performance. ECOLIFE builds on the key insight of intelligently exploiting multi-generation hardware to achieve high performance an
Externí odkaz:
http://arxiv.org/abs/2409.02085
This survey offers a comprehensive overview of recent advancements in Large Language Model (LLM) serving systems, focusing on research since the year 2023. We specifically examine system-level enhancements that improve performance and efficiency with
Externí odkaz:
http://arxiv.org/abs/2407.12391
The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This paper presen
Externí odkaz:
http://arxiv.org/abs/2403.12900
Autor:
Zhao, Dan, Samsi, Siddharth, McDonald, Joseph, Li, Baolin, Bestor, David, Jones, Michael, Tiwari, Devesh, Gadepally, Vijay
As research and deployment of AI grows, the computational burden to support and sustain its progress inevitably does too. To train or fine-tune state-of-the-art models in NLP, computer vision, etc., some form of AI hardware acceleration is virtually
Externí odkaz:
http://arxiv.org/abs/2402.18593
Autor:
Huang, Zijie, Li, Baolin, Asgharzadeh, Hafez, Cocos, Anne, Liu, Lingyi, Cox, Evan, Wise, Colby, Lamkhede, Sudarshan
Given a set of candidate entities (e.g. movie titles), the ability to identify similar entities is a core capability of many recommender systems. Most often this is achieved by collaborative filtering approaches, i.e. if users co-engage with a pair o
Externí odkaz:
http://arxiv.org/abs/2312.04071
Autor:
Samsi, Siddharth, Zhao, Dan, McDonald, Joseph, Li, Baolin, Michaleas, Adam, Jones, Michael, Bergeron, William, Kepner, Jeremy, Tiwari, Devesh, Gadepally, Vijay
Large language models (LLMs) have exploded in popularity due to their new generative capabilities that go far beyond prior state-of-the-art. These technologies are increasingly being leveraged in various domains such as law, finance, and medicine. Ho
Externí odkaz:
http://arxiv.org/abs/2310.03003
Autor:
Li, Baolin, Roy, Rohan Basu, Wang, Daniel, Samsi, Siddharth, Gadepally, Vijay, Tiwari, Devesh
The rapid growth in demand for HPC systems has led to a rise in carbon footprint, which requires urgent intervention. In this work, we present a comprehensive analysis of the carbon footprint of high-performance computing (HPC) systems, considering t
Externí odkaz:
http://arxiv.org/abs/2306.13177
Publikováno v:
Gong-kuang zidonghua, Vol 41, Iss 8, Pp 38-42 (2015)
In order to promote application of acoustic emission monitoring technology in effect evaluation of coal seam hydraulic fracturing, coal seam hydraulic fracturing process was monitored by use of coal and rock dynamic disaster acoustoelectric monitor,
Externí odkaz:
https://doaj.org/article/ee85f85fffd74df9ac4b2106f1373a48
This paper presents a solution to the challenge of mitigating carbon emissions from hosting large-scale machine learning (ML) inference services. ML inference is critical to modern technology products, but it is also a significant contributor to carb
Externí odkaz:
http://arxiv.org/abs/2304.09781