arXiv subjects

Sa Wang

Publications and source records attributed to Sa Wang.

34 records · Page 2Linked to original sources

arXiv2024

MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool

Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations extend the lifespan and domain of the KV cache, necessitating a new architectural approach. We present MemServe, a unified system that integrates both inter-request and intra-request optimizations. MemServe introduces MemPool, an elastic memory pool managing distributed memory and KV caches across serving instances. Using MemPool APIs, MemServe combines context caching with disaggregated inference for the first time, supported by a global scheduler that enhances cache reuse through a global prompt tree-based locality-aware policy. Tests show that MemServe significantly improves job completion time and time-to-first-time.

cs.DC↗

arXiv2024

Transverse momentum balance of dijets in Xe+Xe collisions at the LHC

We present a theoretical study of the medium modifications of the $p_T$ balance ($x_J$) of dijets in Xe+Xe collisions at $\sqrt{s_{NN}}=5.44$ TeV. The initial production of dijets was carried out using the POWHEG+PYTHIA8 prescription, which matches the next-to-leading-order (NLO) QCD matrix elements with the parton shower (PS) effect. The SHELL model described the in-medium evolution of nucleus-nucleus collisions using a transport approach. The theoretical results of the dijet $x_J$ in the Xe+Xe collisions exhibit more imbalanced distributions than those in the p+p collisions, consistent with recently reported ATLAS data. By utilizing the Interleaved Flavor Neutralisation, an infrared-and-collinear-safe jet flavor algorithm, to identify the flavor of the reconstructed jets, we classify dijets processes into three categories: gluon-gluon ($gg$), quark-gluon ($qg$), and quark-quark ($qq$), and investigated the respective medium modification patterns and fraction changes of the $gg$, $qg$, and $qq$ components of the dijet sample in Xe+Xe collisions. It is shown that the increased fraction of $qg$ component at a small $x_J$ contributes to the imbalance of the dijet; in particular, the $q_1g_2$ (quark-jet-leading) dijets experience more significant asymmetric energy loss than the $g_1q_2$ (gluon-jet-leading) dijets traversing the QGP. By comparing the $Δ\langle x_J\rangle = \langle x_J \rangle_{pp} - \langle x_J \rangle_{AA}$ of inclusive, $c\bar{c}$ and $b\bar{b}$ dijets in Xe+Xe collisions, we observe $Δ\langle x_J \rangle_{incl.}>Δ\langle x_J \rangle_{c\bar{c}}>Δ\langle x_J \rangle_{b\bar{b}}$. Moreover, $ρ_{Xe, Pb}$, the ratios of the nuclear modification factors of dijets in Xe+Xe to those in Pb+Pb, were calculated, which indicates that the yield suppression of dijets in Pb+Pb is more pronounced than that in Xe+Xe owing to the larger radius of the lead nucleus.

hep-ph↗

arXiv2024

Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct characteristics of these phases, leading to significant interference. To mitigate interference, our insight is to carefully schedule and group inference requests based on their characteristics. We realize this idea in TetriInfer through three pillars. First, it partitions prompts into fixed-size chunks so that the accelerator always runs close to its computationsaturated limit. Second, it disaggregates prefill and decode instances so each can run independently. Finally, it uses a smart two-level scheduling algorithm augmented with predicted resource usage to avoid decode scheduling hotspots. Results show that TetriInfer improves time-to-first-token (TTFT), job completion time (JCT), and inference efficiency in turns of performance per dollar by a large margin, e.g., it uses 38% less resources all the while lowering average TTFT and average JCT by 97% and 47%, respectively.

cs.DC↗

arXiv2023

Longitudinal momentum fraction of heavy-flavor mesons in jets in high-energy nuclear collisions

Heavy-flavor jets are powerful tools to gain insight into the in-medium partonic energy-loss mechanisms and the quark-gluon plasma's (QGP) transport properties in high-energy nuclear collisions. In this work we present the first theoretical study of the longitudinal momentum fraction $z_{||}$ carried by heavy-flavor mesons in jets in Pb+Pb collisions at $\sqrt{s_{\rm NN}}$ = 5.02 TeV. The p+p baseline is provided by POWHEG+PYTHIA8, which matches the next-to-leading-order hard processes with the parton shower. We employ a Monte Carlo transport model, which considers the collisional and radiative partonic energy loss, to simulate the evolution of heavy-flavor jets in the expanding QGP medium. We observe steeper $z_{||}$ distributions of $\rm{B^0}$ jets compared to those of $\rm{D^0}$ jets at the same kinematics region in p+p collisions, which may be a hint of the harder jet fragmentation function of b jets compared to c jets in vacuum. In A+A collisions, it is shown that the jet quenching effect would generally decrease the values of $z_{||}$. We have made a systematical study on how several factors, including jet $p_{\rm{T}}$, jet radius $R$, and collision centrality, would influence the medium modification of $z_{||}$ distributions of a $\rm{D^0}$ jet. In addition, we predict visibly stronger nuclear modifications of $\rm{B^0}$-jet $z_{||}$ distributions compared to a $\rm{D^0}$ jet within the same $p_{\rm T}$ windows as a result of the much steeper initial $z_{||}$ distribution of the $\rm{B^0}$ jet in vacuum.

hep-ph↗

arXiv2023

$Z^0$ boson associated b-jet production in high-energy nuclear collisions

The production of vector boson tagged heavy quark jets potentially provides new tools to probe the jet quenching effect. In this paper, we present the first theoretical study on the angular correlations ($Δϕ_{bZ}$), transverse momentum imbalance ($x_{bZ}$), and nuclear modification factor ($I_{AA}$) of $Z^0$ boson tagged b-jets in heavy-ion collisions, which was performed using a Monte Carlo transport model. We find that the medium modification of the $Δϕ_{bZ}$ for $Z^0\,+\,$b-jet has a weaker dependence on $Δϕ_{bZ}$ than that for $Z^0\,+\,$jet, and the modification patterns are sensitive to the initial jet $p_T$ distribution. Additionally, with the high purity of the quark jet in $Z^0\,+\,$(b-)jet production, we calculate the momentum imbalance $x_{bZ}$ and the nuclear modification factor $I_{AA}$ of $Z^0\,+\,$b-jet in Pb+Pb collisions. We observe a smaller $Δ\left\langle x_{jZ} \right\rangle$ and larger $I_{AA}$ of $Z^0\,+\,$b-jet in Pb+Pb collisions relative to those of $Z^0\,+\,$jet, which may be an indication of the mass effect of jet quenching and can be tested in future measurements.

hep-ph↗

arXiv2023

Heavy-Flavour Jets in High-Energy Nuclear Collisions

Reconstructed jets initiated from heavy quarks provide a powerful tool to probe the properties of the quark-gluon plasma (QGP) and to explore the mass hierarchy of jet quenching. In this article, we review the recent theoretical progresses on heavy-flavour jets in high-energy nuclear collisions at the RHIC and LHC. We focus on the yields and substructures of charm and bottom quark jets with jet quenching effect, such as the nuclear modification factors, transverse momentum imbalance, angular correlation, radial profiles, fragmentation functions, the "dead-cone" effect, etc.

nucl-th↗

arXiv2022

INTERNEURON: A Middleware with Multi-Network Communication Reliability for Infrastructure Vehicle Cooperative Autonomous Driving

Infrastructure-Vehicle Cooperative Autonomous Driving (IVCAD) is a new paradigm of autonomous driving, which relies on the cooperation between intelligent roads and autonomous vehicles. This paradigm has been shown to be safer and more efficient compared to the on-vehicle-only autonomous driving paradigm. Our real-world deployment data indicates that the effectiveness of IVCAD is constrained by reliability and performance of commercial communication networks. This paper targets this exact problem, and proposes INTERNEURON, a middleware to achieve high communication reliability between intelligent roads and autonomous vehicles, in the context of IVCAD. Specifically, INTERNEURON dynamically matches IVCAD applications and the underlying communication technologies based on varying communication performance and quality needs. Evaluation results confirm that INTERNEURON reduces deadline violations by more than 95\%, significantly improving the reliability of IVCAD systems.

cs.RO↗

arXiv2022

Probing the in-medium $P_T$-broadening by $γ$+HF angular de-correlations

Angular correlations between vector boson and heavy flavors~(HF) are potentially new effective tools to gain insight into the partonic interactions in the quark-gluon plasma (QGP). In this paper, we present the theoretical study of the azimuthal angular de-correlations of $γ+$HF in nucleus-nucleus collisions as a new probe of the in-medium $P_T$-broadening effect. The initial production of $γ+$HF in p+p is generated by SHERPA which matches the next-to-leading hard processes with parton shower. The in-medium heavy quark evolution is implemented by a Monte Carlo Langevin simulation, which takes into account the collisional and radiative energy loss. We observe considerable suppression at $Δϕ_{γD}\simπ$ and enhancement at $Δϕ_{γD}<2.8$ in $γ+$D azimuthal angular distribution in $0-10\%$ Pb+Pb collisions at $\sqrt{s_{NN}}=$5.02 TeV compared to the p+p baseline, which indicates evident in-medium $P_T$-broadening of charm quarks. We also find that the overall modification patterns of $γ+$D angular distribution are sensitive to the selection cut of D meson $p_T$. Furthermore, by constructing the 2D ($x_{J}^{γD}, Δϕ_{γD}$) correlation diagram, it's possible to display the respective impacts of the two aspects of jet quenching, energy loss and $P_T$-broadening, on the final-state $γ+$D observable simultaneously. Additionally, we find weaker angular de-correlations of $γ+$B compared to $γ+$D which may be helpful to understand the mass hierarchy in heavy-ion collisions. Finally, the nuclear modification of $Δϕ_{γD}$ distributions in central $0-10\%$ Au+Au collisions at RHIC energy is provided for completeness.

nucl-th↗

arXiv2021

Radial profile of bottom quarks in jets in high-energy nuclear collisions

Angular correlations between heavy quark (HQ) and its tagged jet are potentially new tools to gain insight into the in-medium partonic interactions in relativistic heavy-ion collisions. In this work, we present the first theoretical study on the radial profiles of B mesons in jets in Pb+Pb collisions at the LHC. The initial production of bottom quark tagged jet in p+p is computed by SHERPA which matches the next-to-leading order matrix elements with contributions of parton shower, whereas the massive quark traversing the QGP described by a Monte Carlo model SHELL which can simultaneously simulate light and heavy flavor in-medium energy loss within the framework of Langevin evolution. In p+p collisions, we find that at lower $p_T^Q$ the radial profiles of heavy flavors in jets are sensitive to the heavy quark mass. In $0-10\%$ Pb+Pb collisions at $\rm \sqrt{s_{NN}}=5.02$ TeV, we observe an inverse modification pattern of the B mesons radial profiles in jets at $\rm 4 20$ GeV region naturally has a narrower initial distribution and consequently leads to a narrower modification pattern of radial profile; however the diffusion nature of the heavy flavor in-medium interactions will give rise to a broader modification pattern of radial profile. These two effects consequently compete and offset with each other, and the b quarks in jets benefit more from the former and suffers less diffusion effect compared to that of c quarks in jets. These findings can be tested in the future experimental measurements at the LHC to gain better understanding of the mass effect of jet quenching.

nucl-th↗

arXiv2020

Radial profile of heavy quarks in jets in high-energy nuclear collisions

In high energy nuclear collisions, heavy flavor tagged jets are useful hard probes to study the properties of the quark-gluon plasma (QGP). In this talk, we present the first theoretical prediction of the $D^0$ meson radial distributions in jets relative to the jet axis both in p+p and Pb+Pb collisions at $5.02$ TeV, it shows a nice agreement with the available experimental data. The in-medium jet evolution in the study is described by a Monte Carlo transport model which has been incorporated with the initial events as input provided by the next-to-leading order (NLO) plus parton shower (PS) event generator SHERPA. In such evolution process, both elastic and inelastic parton energy loss in the hot and dense medium are taken into account. Within this same simulation framework, we predict different modification patterns of the radial profile of charm and bottom quarks in jets in Pb+Pb collisions: jet quenching effect will lead the charm quarks diffuse to lager radius while lead the bottom quarks distributed closer to jet axis.

nucl-th↗

arXiv2020

Transverse Momentum Balance and Angular Distribution of $b\bar{b}$ Dijets in Pb+Pb collisions

The productions of inclusive b-jet and $b\bar{b}$ dijets in Pb+Pb collisions have been investigated by considering the heavy quark and the light quark in-medium evolution simultaneously. The initial hard processes of inclusive b-jet and $b\bar{b}$ dijets productions are described by a next-to-leading order (NLO) plus parton shower Monte Carlo (MC) event generator SHERPA which can be well-matched with the experimental data in p+p collisions. The framework combines the Langevin transport model to describe the evolution of the bottom quark also its collisional energy loss and the higher-twist description to consider the radiative energy loss of both the bottom and light quarks. We compare the theoretical simulation of inclusive jet and inclusive b-jet $R_{\rm AA}$ in Pb+Pb collisions at $\sqrt{s_{\rm NN}}=2.76$ TeV with the experimental data, and then present the theoretical simulation of the momentum balance of the $b\bar{b}$ dijet in Pb+Pb collisions at $5.02$ TeV with the recent CMS data for the first time. A similar trend as that in inclusive dijets has been observed in $b\bar{b}$ dijets, the production distribution is shifted to smaller $x_J$ due to the jet quenching effect. At last, the prediction of the normalized azimuthal angle distribution of the $b\bar{b}$ dijet in Pb+Pb collisions at $5.02$ TeV has been reported. The medium induced energy loss effect of the $b\bar{b}$ dijets will overall suppress its production, but the same side ($Δϕ\to 0$ region) suffers more energy loss than away side ($Δϕ\to π$ region), therefore lead to the suppression on the same side and the enhancement on the away side in the normalized azimuthal angle distribution in A+A collisions.

nucl-th↗

arXiv2020

Radial distribution of charm quarks in jets in high-energy heavy-ion collisions

Heavy flavor physics in high-energy heavy-ion collisions is a promising and active area to study the mass dependence of the "jet quenching" effects both at the RHIC and the LHC. In this talk, we present the first theoretical study on the $D^0$ meson radial distributions relative to the jet axis both in p+p and Pb+Pb collisions at $\sqrt{s_{NN}}=5.02$ TeV, where a nice agreement of our results with experimental data is observed. The in-medium parton propagations are described by a Monte Carlo transport model which uses the next-to-leading order (NLO) plus parton shower (PS) event generator SHERPA as input and includes elastic (collisional) and inelastic (radiative) in-medium interaction of heavy flavor jet. We find that, at low $D^0$ meson $p_T$, the radial distribution significantly shifts to larger radius indicating a strong diffusion effect, and the diffusion effects decrease quickly with $p_T$ ,which is consistent with the recent CMS measurements. We demonstrate that the angular deviation of charm quarks is sensitive to $D_s$ but not $\hat{q}$, which may provide new constrains on the collisional and radiative heavy quark energy loss.

nucl-th↗

arXiv2019

Diffusion of charm quarks in jets in high-energy heavy-ion collisions

The radial distribution of $D^0$ mesons in jets probes the diffusion of charm quark relative to the jet axis and provides a new perspective to study the interaction mechanisms between heavy quarks and the medium in the nucleus-nucleus collisions. The in-medium parton propagations are described by a Monte Carlo transport model which uses the next-to-leading order (NLO) plus parton shower (PS) event generator SHERPA as input and includes elastic (collisional) and inelastic (radiative) interaction for heavy quarks as well as light partons. At low $D^0$ meson $p_T$, the radial distribution significantly shifts to larger radius indicating a strong diffusion effect which is consistent with the recent experimental data. We demonstrate that the angular deviation of charm quarks declines with $p_T$ and is very sensitive to the collisional more than radiative interaction at $p_T<5$~GeV. As predictions, we present the $D^0$ meson radial distribution in jets in p+p and $0-10\%$ Au+Au collisions at $\sqrt{s_{NN}}=200$~GeV at the RHIC, and also estimate the nuclear modification factor of charm jet in central Au+Au collisions at 200~GeV at the RHIC and central Pb+Pb collisions at $5.02$~TeV at the LHC.

nucl-th↗

arXiv2018

The production of $b\bar{b}$ dijet in heavy-ion collisions at the LHC

We report our recent theoretical calculations for $b\bar{b}$ dijet production in high-energy nuclear collisions. The NLO+parton shower (PS) event generator SHERPA has been employed to provide the pp baseline of $b\bar{b}$ dijet production. A framework which combines Langevin transport equation to describe the evolution of heavy quarks and the higher-twist scheme to consider the inelastic energy loss of both light and heavy partons has been implemented. Within this framework, we present the theoretical result of transverse momentum imbalance $x_J=p_{T1}/p_{T2}$ both for inclusive dijet and $b\bar{b}$ dijet in Pb+Pb collision at 5.02 TeV. The energy loss of b jet would shift $x_J$ to smaller value relative to p+p reference which is consistent with the CMS data. In addition, we show the medium modification for angular correlation of $b\bar{b}$ dijet in A+A collision at $\sqrt{s_{NN}}=5.02$~TeV. We observe a stronger suppression in small $Δϕ=|ϕ_{b1}-ϕ_{b2}|$ region where the gluon splitting processes dominate relative to large $Δϕ$ region. The difference leads to a modest suppression on near side ($Δϕ\sim 0$) and enhancement on away side ($Δϕ\simπ$).

nucl-th↗

arXiv2018

Jet tomography in high-energy nuclear collisions

When an energetic parton traversing the QCD medium, it may suffer multiple scatterings and lose energy. This jet quenching phenomenon may lead to the suppression of leading hadron productions as well as medium modifications of full jet observables in heavy-ion collisions. In this talk we discuss the nuclear modification factors and yield ratios of identified meson such as $η$, $ρ^0$, $ϕ$, $ω$, and $K^0_{\rm S}$ as well as $π$ meson at large $p_T$ in A+A collisions at the next-to-leading order (NLO) with high-twist approach of parton energy loss. Then we discuss a newly developed formalism of combing NLO matrix elements and parton shower (PS) for initial hard production with parton energy loss in the QGP, and its application in investigating massive gauge boson ($Z^0$/$W^{\pm}$) tagged jet productions and $b\bar{b}$ dijet correlations in Pb+Pb at the LHC.

nucl-th↗

arXiv2018

Avalon: Building an Operating System for Robotcenter

This paper envisions a scenario that hundreds of heterogeneous robots form a robotcenter which can be shared by multiple users and used like a single powerful robot to perform complex tasks. However, current multi-robot systems are either unable to manage heterogeneous robots or unable to support multiple concurrent users. Inspired by the design of modern datacenter OSes, we propose Avalon, a robot operating system with two-level scheduling scheme which is widely adopted in datacenters for Internet services and cloud computing. Specifically, Avalon integrates three important features together: (1) Instead of allocating a whole robot, Avalon classifies fine-grained robot resources into three categories to distinguish which fine-grained resources can be shared by multi-robot frameworks simultaneously. (2) Avalon adopts a location based resource allocation policy to substantially reduce scheduling overhead. (3) Avalon enables robots to offload computation intensive tasks to the clouds.We have implemented and evaluated Avalon on robots on both simulated environments and real world.

cs.RO↗