research
< From left: Professor Jongse Park , M.S candidate Jaehong Cho, M.S candidate Hyunmin Choi, Professor Brandon Reagen ISPASS >
Operating Large Language Model (LLM) services like ChatGPT requires a server infrastructure on the scale of tens of thousands of units. However, constructing actual equipment every time a new AI semiconductor or system architecture needs to be verified incurs massive costs and time. A research team at our university has developed a ‘virtual testbed’ that can pre-verify performance and efficiency inside a computer before building an actual large-scale AI server.
KAIST announced on May 29th that the research on a Large Language Model (LLM) serving infrastructure simulator (virtual testing software) developed by Professor Jongse Park’s research team in the School of Computing won the Best Paper Award at ‘ISPASS 2026 (IEEE International Symposium on Performance Analysis of Systems and Software),’ a world-renowned conference in the field of computer system performance analysis.
‘LLMServingSim 2.0,’ developed by the research team, is a simulation platform capable of virtually analyzing various hardware and software combinations in complex AI service environments. Researchers and developers can freely experiment with various design options and verify performance without having to directly build expensive, large-scale server infrastructures.
< LLMServingSim 2.0 is workload >
In particular, this technology is drawing attention because it goes beyond the existing Graphics Processing Unit (GPU)-centric environment to support diverse hardware environments, including Neural Processing Units (NPUs), which are rising as next-generation AI semiconductors, and Processing-In-Memory (PIM, a semiconductor technology that performs operations inside the memory).
In other words, it is a technology that allows future-oriented AI semiconductors that have not yet been commercialized to be tested in advance within a virtual datacenter environment. Through this, it is possible to replicate and analyze inside a computer how much the service speed improves, how much power consumption is reduced, and whether it operates stably even in a server environment scaled to tens of thousands of units when a specific semiconductor is applied.
In addition, it reproduces complex operations that occur during actual AI service operations—such as data processing, request distribution, and memory utilization—at the system level, enabling performance evaluations that are close to reality. Notably, it can even analyze disaggregated infrastructure environments where multiple server resources are separated and connected for use, showing great potential for utilization in next-generation AI datacenter research.
This simulator is expected to be widely utilized not only by researchers but also by LLM service companies and AI semiconductor startups to design and optimize next-generation AI infrastructures. This is because it can rapidly verify new AI semiconductors or service architectures prior to actual construction, thereby significantly reducing the cost and time of AI infrastructure development.
< Research Image (AI-generated image) >
Professor Jongse Park said, “The competitiveness of AI services is determined not only by the model itself but also by the infrastructure technology that operates it stably and efficiently.” He added, “We hope this simulator will serve as an important foundation for researchers and the industry to develop next-generation AI infrastructures faster and more efficiently.”
This research was led by M.S candidate Jaehong Cho and Hyunmin Choi in the School of Computing as co-first authors. Following their Best Paper Award at the 2024 IISWC (IEEE International Symposium on Workload Characterization), the research team won the Best Paper Award again at this ISPASS 2026, proving their research competitiveness in the field of AI infrastructure once more.
※ Paper Title: LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure, DOI: 10.1109/ISPASS69572.2026.00012 (Authors: Jaehong Cho, Hyunmin Choi, Guseul Heo, Jongse Park) ※ Open Source Link:
-
research KAIST Identifies Cause of Artifacts in Battery Nanoscale Analysis, Paving the Way for More Reliable Measurements
A signal that appears to show ions moving inside a battery may, in fact, be an illusion caused by an uneven surface. A KAIST research team has identified the origin of this type of artifacts, which can lead researchers to misinterpret what is happening inside a battery, and has developed a method to reduce it. The findings are expected to enable more accurate analysis of ion movement and improve the reliability of next-generation battery-material development, including that of solid-state and
2026-09-07 -
research Weak Hydrogen Bonds Dethrone Copper's Stability, Opening a New Path for Ion Selection
Copper has been knocked off the top of a stability ranking it had dominated for decades. Without altering the atoms directly bonded to the metal, a KAIST research team reversed the longstanding trend in which copper generally forms the most stable complexes by tuning only the weak hydrogen bonds in its surrounding environment. The findings could open new avenues for selective metal separation and recognition, as well as catalyst design. KAIST (President Choongsik Bae) announced on September 6
2026-09-07 -
people KAIST Professor Jaekyung Kim Selected as One of Asia's 12 Next-Generation Scientists
KAIST (President Choongsik Bae) announced on September 4 that Professor Jaekyung Kim from the Department of Biological Sciences has been selected as a Fellow of the “2026 Asian Young Scientist Fellowship (AYSF),” a program that supports promising young scientists across Asia. The Asian Young Scientist Fellowship (AYSF) is a privately funded research fellowship in Asia, established to support young scientists in carrying out creative and challenging research. Since selecting its fi
2026-09-04 -
research KAIST Develops AI Technology That Fixes SQL Errors Without Starting Over
“Find the best-selling product from last year.” When an AI system attempts to answer a question like this by querying a company database, even a single reference to a nonexistent item can cause the query to fail. Until now, correcting such an error often required regenerating the entire SQL query from scratch. A KAIST research team has developed a technology that instead identifies and fixes only the erroneous part. The technology is expected to make AI-powered data retrieval faste
2026-09-04 -
research KAIST Tames a Semiconductor Greenhouse Gas 6,000 Times More Potent Than CO₂ with the ‘Power of Disorder’
Among the gases used in semiconductor manufacturing, tetrafluoromethane (CF₄) is a greenhouse gas over 6,000 times more potent than carbon dioxide. A KAIST research team has developed a technology that removes this gas with high efficiency while extending the usable lifetime of the catalyst that helps break it down by harnessing the ‘power of disorder,’ in which mixing multiple metal atoms together actually stabilizes the catalyst’s structure. KAIST (President Choongsik Bae)
2026-09-03