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:20260728T175500
DTEND;TZID=America/Los_Angeles:20260728T175600
UID:dac_DAC 2026_sess317_RESEARCH292@linklings.com
SUMMARY:Throughput-Oriented Speculative Decoding via Intra-Device Parallel
 ism
DESCRIPTION:Zehua Li (Xi'an Jiaotong University), Zijian Zhu (Tsinghua Uni
 versity), Zhanhong Tan (PolarBear Tech), and Fei Ren and Kaisheng Ma (Tsin
 ghua University)\n\nLarge Language Model (LLM) serving is crucial for appl
 ications like chatbots\nand code assistants, yet its implementation remain
 s bottlenecked by low hardware utilization. Speculative decoding improves 
 effective throughput, but still suffers from suboptimal resource partition
 ing. We introduce SmoothSpec, a speculative decoding system designed to ma
 ximize serving throughput by fully leveraging intra-device parallelism. Sm
 oothSpec deploys draft and target models with the same parallelism configu
 rations but allocates asymmetric compute resources at runtime. We design a
  novel scheduling strategy that dynamically adjusts both the draft paramet
 ers for the next step and the resource allocation ratio between the two mo
 dels, based on the generation quality of draft tokens. We implement Smooth
 Spec on a single-node LLM serving system and demonstrate its effectiveness
  across diverse workloads.\n\nTrack: EDA7-II. Physical Design and Verifica
 tion, Design\n\nSession Chairs: Christian Pilato (Politecnico di Milano); 
 Mohsen Imani (University of California, Irvine); Flavio Ponzina (San Diego
  State University); Amin Farshidi (Cadence Design Systems, Inc.); Yonggan 
 Fu (Georgia Institute of Technology, NVIDIA); Dimitrios Tsaras (Huawei, Ho
 ng Kong University of Science and Technology (HKUST)); Anh Nguyen (Fujitsu
  Limited); Ruiyang Qin (Villanova University); Jiliang Zhang (Hunan Univer
 sity); Meng Li (Peking University); and Rassul Bairamkulov (Advanced Micro
  Devices (AMD))\n\n
END:VEVENT
END:VCALENDAR