Ying Sheng

Ying Sheng

Auto-generated profile, based on publicly available information

Ying Sheng

Stanford University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2023
Verified
Conference Paper
Open access
WKWoosuk Kwon
Woosuk Kwon
ZLZhuohan Li
Zhuohan Li
SZSiyuan Zhuang
Siyuan Zhuang
YSYing Sheng
Ying Sheng
LZLianmin Zheng
Lianmin Zheng
ISIon Stoica
Ion Stoica

30 March 2022
Verified
Book Chapter
Open access
PDF file
HBHaniel Barbosa
Haniel Barbosa
CBClark Barrett
Clark Barrett
MBMartin Brain
Martin Brain
GKGereon Kremer
Gereon Kremer
HLHanna Lachnitt
Hanna Lachnitt
YZYoni Zohar
Yoni Zohar
Cvc5 is the latest SMT solver in the cooperating validity checker series and builds on the successful code base of CVC4. This paper serves as a comprehensive system description of cvc5 ’s architectural design and highlights the major features and components introduced since CVC4 1.8. We evaluate cvc5 ’s performance on all benchmarks in SMT-LIB and provide a comparison against CVC4 and Z3.

17 July 2024
Verified
Book Chapter
Closed access
PDF file
CSChuyue Sun
Chuyue Sun
YSYing Sheng
Ying Sheng
OPOded Padon
Oded Padon
CBClark Barrett
Clark Barrett

30 March 2025
Verified
Conference Paper
Open access
SCShiyi Cao
Shiyi Cao
SLShu Liu
Shu Liu
TGTyler Griggs
Tyler Griggs
PSPeter Schafhalter
Peter Schafhalter
XLXiaoxuan Liu
Xiaoxuan Liu
ISIon Stoica
Ion Stoica
Efficient deployment of large language models, particularly Mixture of Experts (MoE) models, on resource-constrained platforms presents significant challenges in terms of computational efficiency and memory utilization. The MoE architecture, renowned for its ability to increase model capacity without a proportional increase in inference cost, greatly reduces the token generation latency compared with dense models. However, the large model size makes MoE models inaccessible to individuals without high-end GPUs. In this paper, we propose a high-throughput MoE batch inference system, MoE-Lightning, that significantly outperforms past work. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization, and a performance model, HRM, based on a Hierarchical Roofline Model we introduce to help find policies with higher throughput than existing systems. MoE-Lightning can achieve up to (10.3x) higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB). When the theoretical system throughput is bounded by the GPU memory, MoE-Lightning can reach the throughput upper bound with 2-3x less CPU memory, significantly increasing resource utilization. MoE-Lightning also supports efficient batch inference for much larger MoEs (e.g., Mixtral 8x22B and DBRX) on multiple low-cost GPUs (e.g., 2--4 T4s).

5 May 2022 in Journal of Automated Reasoning
Verified
Journal Article
Closed access
PDF file
YSYing Sheng
Ying Sheng
YZYoni Zohar
Yoni Zohar
CRChristophe Ringeissen
Christophe Ringeissen
JLJane Lange
Jane Lange
PFPascal Fontaine
Pascal Fontaine
CBClark Barrett
Clark Barrett

1 August 2022
Verified
Book Chapter
Open access
PDF file
YSYing Sheng
Ying Sheng
ANAndres Nötzli
Andres Nötzli
ARAndrew Reynolds
Andrew Reynolds
YZYoni Zohar
Yoni Zohar
DDDavid Dill
David Dill
CTCesare Tinelli
Cesare Tinelli
Dynamic arrays, also referred to as vectors, are fundamental data structures used in many programs. Modeling their semantics efficiently is crucial when reasoning about such programs. The theory of arrays is widely supported but is not ideal, because the number of elements is fixed (determined by its index sort) and cannot be adjusted, which is a problem, given that the length of vectors often plays an important role when reasoning about vector programs. In this paper, we propose reasoning about vectors using a theory of sequences. We introduce the theory, propose a basic calculus adapted from one for the theory of strings, and extend it to efficiently handle common vector operations. We prove that our calculus is sound and show how to construct a model when it terminates with a saturated configuration. Finally, we describe an implementation of the calculus in cvc5 and demonstrate its efficacy by evaluating it on verification conditions for smart contracts and benchmarks derived from existing array benchmarks.