BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T174000
DTEND;TZID=America/Los_Angeles:20260728T174000
UID:dac_DAC 2026_sess317_RESEARCH538@linklings.com
SUMMARY:Amoeba: Runtime Tensor Parallel Transformation for LLM Inference S
 ervices
DESCRIPTION:Haoyu Chen (Fudan University), Xue Li (Alibaba Group), Kun Qia
 n and Yu Guan (Alibaba), and Jin Zhao and Xin Wang (Fudan University)\n\nI
 n Large Language Model (LLM) inference services, it is challenging to make
  a parallelism strategy configuration, to efficiently process the requests
  of variance context lengths. Requests of long context require high degree
  of parallelism to provide more memory for Key-Value (KV) Cache, while req
 uests of short context prefer low degree of parallelism to increase concur
 rency, thus improving throughput.\n\nTo maintain high throughput while sup
 porting large context lengths on demand, we propose Amoeba, a runtime Tens
 or Parallel (TP) transformation for online LLM inference services, which a
 daptively adjusts the TP of running instances to align with the dynamics o
 f incoming requests. Evaluations using real-world traces show that Amoeba 
 improves throughput by 1.75×-6.57× compared to state-of-the-art solutions.
 \n\nTrack: EDA7-II. Physical Design and Verification, Design\n\nSession Ch
 airs: Christian Pilato (Politecnico di Milano); Mohsen Imani (University o
 f California, Irvine); Flavio Ponzina (San Diego State University); Amin F
 arshidi (Cadence Design Systems, Inc.); Yonggan Fu (Georgia Institute of T
 echnology, NVIDIA); Dimitrios Tsaras (Huawei, Hong Kong University of Scie
 nce and Technology (HKUST)); Anh Nguyen (Fujitsu Limited); Ruiyang Qin (Vi
 llanova University); Jiliang Zhang (Hunan University); Meng Li (Peking Uni
 versity); and Rassul Bairamkulov (Advanced Micro Devices (AMD))\n\n
END:VEVENT
END:VCALENDAR