ARXIV:2602.23036 · INFRASTRUCTURE SIMULATION · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

arXiv

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Evidence 0 refs | 0 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly…

METHOD

Full abstract

Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency. As a result, LLM serving performance is no longer determined by hardware or software choices in isolation, but by their runtime interaction through scheduling, data movement, and interconnect behavior. However, understanding these interactions remains challenging, as existing simulators lack the ability to jointly model heterogeneous hardware and disaggregated serving techniques within a unified, runtime-driven framework. This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions in heterogeneous and disaggregated LLM serving infrastructures explicit and analyzable. LLMServingSim 2.0 embeds serving decisions and hardware behavior into a single runtime loop, enabling interaction-aware modeling of batching, routing, offloading, memory, and power. The simulator supports extensible integration of emerging accelerators and memory systems through profile-based modeling, while capturing dynamic serving behavior and system-level effects. We validate LLMServingSim 2.0 against real deployments, showing that it reproduces key performance, memory, and power metrics with an average error of 0.97%, while maintaining simulation times of around 10 minutes even for complex configurations. These results demonstrate that LLMServingSim 2.0 provides a practical bridge between hardware innovation and serving-system design, enabling systematic exploration and co-design for next-generation LLM serving infrastructures.

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components…

WHY NOW

Infrastructure Simulation moved forward this cycle; last verified April 2026. Public score 3.0/10. Implementation evidence is present through a linked repository.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainDevelop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Evidence0 refs | 0 sources | 50% coverage

Blockermissing authors

Analysis summary

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2602.23036 · INFRASTRUCTURE SIMULATION · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

arXiv

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Evidence 0 refs | 0 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Infrastructure Simulation moved forward this cycle; last verified April 2026. Public score 3.0/10. Implementation evidence is present through a linked repository.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainDevelop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Evidence0 refs | 0 sources | 50% coverage

Blockermissing authors

Analysis summary

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2602.23036

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 50% coverage.

What was readable

linkedon filenot materializedderived fallback58 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

3.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Infrastructure Simulation moved forward this cycle; last verified April 2026. Public score 3.0/10. Implementation evidence is present through a linked repository.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 3.0/10 on the public viability pass. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency. A public repository is linked, so build verification can inspect implementation evidence instead of treating the paper as PDF-only.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Infrastructure Simulation moved forward this cycle; last verified April 2026. Public score 3.0/10. Implementation evidence is present through a linked repository.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Infrastructure Simulation

Competitors

not indexed

Competitive landscape

Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.

Segment

Infrastructure Simulation

Adoption evidence

Public code linked for build inspection

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.23036 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(58)

Aegaeon: Effective GPU Pooling for Concurrent LLM Serving on the Market

2025Yuxing Xiang, Xue Li et al.

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

2025Yihua Cheng, Yuhan Liu et al.

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness

2025Huizheng Wang, Zichuan Wang et al.

PNM Meets Sparse Attention: Enabling Multi-Million Tokens Inference at Scale

2025Sookyung Choi, Myunghyun Rhee et al.

AiDE: Attention-FFN Disaggregated Execution for Cost-Effective LLM Decoding on CXL-PNM

2025Kyungsoo Kim, O. Kwon et al.

LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading

2025Hyungyo Kim, Nachuan Wang et al.

Hybe: GPU-NPU Hybrid System for Efficient LLM Inference with Million-Token Context Window

2025Seungjae Moon, Junseo Cha et al.

CXL–GPU: Pushing GPU Memory Boundaries with the Integration of CXL Technologies

2025Donghyun Gouk, Seungkwan Kang et al.

KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider

2025Jiahao Wang, Jinbo Han et al.

Systematic CXL Memory Characterization and Performance Analysis at Scale

2025Jinshu Liu, Hamid Hadian et al.

TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference Systems

2025Feiyang Wu, Zhuohang Bian et al.

ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput

2025Junsoo Kim, Hunjong Lee et al.

InstAttention: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

2025Xiurui Pan, Endian Li et al.

PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System

2025Yintao He, Haiyu Mao et al.

DEEPSERVE: Serverless Large Language Model Serving at Scale

2025Junhao Hu, Jiang Xu et al.

OASIS: Outlier-Aware KV Cache Clustering for Scaling LLM Inference in CXL Memory Systems

2025Minseok Seo, Jungi Hyun et al.

IMPRESS: An Importance-Informed Multi-Tier Prefix KV Storage System for Large Language Model Inference

2025Weijian Chen, Shuibing He et al.

Mooncake: Trading More Storage for Less Computation - A KVCache-centric Architecture for Serving LLM Chatbot

2025Ruoyu Qin, Zheming Li et al.

APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving

2024Yi-Chien Lin, Woosuk Kwon et al.

MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs

2024Shiyi Cao, Shu Liu et al.

Showing 20 of 58 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkFrontier: Towards Comprehensive and Accurate LLM Inference Simulation

3.0

Prior WorkRestoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach

3.0

Extension

Builds On ThisAGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving

0.0

Commercially relevant

Higher ViabilityScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management

5.0

Higher ViabilityOptimizing Service Operations via LLM-Powered Multi-Agent Simulation

7.0

Higher ViabilityE2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments

7.0

Higher ViabilityFlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

4.0

Higher ViabilityEfficient LLM Serving for Agentic Workflows: A Data Systems Perspective

7.0

Higher ViabilityContinuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

6.0

Higher ViabilityKVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

7.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2602.23036
Route: /paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure
Active tab: read
Artifact: llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure/paper-pack
REST build passport API/api/v1/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "02e22e07-cb98-4600-aabb-cc3ca01d437c",
  "arxiv_id": "2602.23036",
  "canonical_route": "/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
  "endpoints": {
    "paper_pack": "/api/v1/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure/paper-pack",
    "build_passport": "/api/v1/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

stale

Proof freshness: stale
Proof status: unverified
Display score: 3/10
Last proof check: 2026-03-19
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 50%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

Canonical ID llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure | Route /paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.23036"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure",
  "normalized_query": "2602.23036",
  "route": "/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
  "paper_ref": "llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Not build-ready: LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

/buildability/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

Ignoreblocked

Subject: LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

Paper ref

llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure

arXiv id

2602.23036

Freshness

Generated at

2026-03-19T18:48:05.835Z

Evidence freshness

stale

Last verification

2026-03-19T18:48:05.835Z

Sources

References

Coverage

50%

Hash state

Lineage hash

019be3671f701555a5e671f46dbc2a4b549e487920acca51af6aaf0cbb62395b

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: references
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet

Verification pending / evidence receipt incomplete

references

distribution_readiness_scores

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure#webpage",
      "url": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
      "name": "LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure",
      "description": "Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure#scholarlyArticle",
      "headline": "LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure",
      "description": "Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.",
      "url": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure",
      "sameAs": "https://arxiv.org/abs/2602.23036",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.23036"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-26T14:22:17.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7b918978febd9142781786aa6733a42f521841a4"
          },
          "url": "https://www.semanticscholar.org/paper/7b918978febd9142781786aa6733a42f521841a4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "55087e6f6392d26af8b341000f20a4cf24db03bf"
          },
          "url": "https://www.semanticscholar.org/paper/55087e6f6392d26af8b341000f20a4cf24db03bf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b499db00e6b1a3c64f43dccc6c8291297d9bf8a8"
          },
          "url": "https://www.semanticscholar.org/paper/b499db00e6b1a3c64f43dccc6c8291297d9bf8a8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "96c50a217d6dfbb1757c93db5fd56c6c595df7c2"
          },
          "url": "https://www.semanticscholar.org/paper/96c50a217d6dfbb1757c93db5fd56c6c595df7c2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7c212205445e7743fbdd3487ba761a0a1e62be0b"
          },
          "url": "https://www.semanticscholar.org/paper/7c212205445e7743fbdd3487ba761a0a1e62be0b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3408b2987ce5b985e1f419496fd03988ed02535d"
          },
          "url": "https://www.semanticscholar.org/paper/3408b2987ce5b985e1f419496fd03988ed02535d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "011b0988befcce465561381ba9802d3f360a1247"
          },
          "url": "https://www.semanticscholar.org/paper/011b0988befcce465561381ba9802d3f360a1247"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cd7e22ebffcfa2bb3a0701d7d118f25eb8c43a87"
          },
          "url": "https://www.semanticscholar.org/paper/cd7e22ebffcfa2bb3a0701d7d118f25eb8c43a87"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "09338cf9b56a3801b86ad398f1c8f095bef413c8"
          },
          "url": "https://www.semanticscholar.org/paper/09338cf9b56a3801b86ad398f1c8f095bef413c8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b416385de173272d3ec934787c387c6758cf41cb"
          },
          "url": "https://www.semanticscholar.org/paper/b416385de173272d3ec934787c387c6758cf41cb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bc8ba4812a829f944846d2c744ae1c2a5109edad"
          },
          "url": "https://www.semanticscholar.org/paper/bc8ba4812a829f944846d2c744ae1c2a5109edad"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "35aca777e0ea4dd2822b3832b8ba2e78b5f05773"
          },
          "url": "https://www.semanticscholar.org/paper/35aca777e0ea4dd2822b3832b8ba2e78b5f05773"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "35b5137a1ce1475c421ce2b04c7343a6f24b6959"
          },
          "url": "https://www.semanticscholar.org/paper/35b5137a1ce1475c421ce2b04c7343a6f24b6959"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "958764de5f17d5477901cda94fc7cbf730be30cd"
          },
          "url": "https://www.semanticscholar.org/paper/958764de5f17d5477901cda94fc7cbf730be30cd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d7fcb7044b03897479232d0cca8f2cf600543c6d"
          },
          "url": "https://www.semanticscholar.org/paper/d7fcb7044b03897479232d0cca8f2cf600543c6d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "19e0edfb65c279427c145afc466b31b7b4a3bb93"
          },
          "url": "https://www.semanticscholar.org/paper/19e0edfb65c279427c145afc466b31b7b4a3bb93"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2e774fd391ff10123af13d60a9efc54548705bc0"
          },
          "url": "https://www.semanticscholar.org/paper/2e774fd391ff10123af13d60a9efc54548705bc0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "07f1fbd2a036d3e75a9fb00b30a413981b7ff17e"
          },
          "url": "https://www.semanticscholar.org/paper/07f1fbd2a036d3e75a9fb00b30a413981b7ff17e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "078970127eaf146df8e8bcfafb86c7728f49b64e"
          },
          "url": "https://www.semanticscholar.org/paper/078970127eaf146df8e8bcfafb86c7728f49b64e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d6e1d2e4697f3d9776010fdfbfc45ffc60e4008d"
          },
          "url": "https://www.semanticscholar.org/paper/d6e1d2e4697f3d9776010fdfbfc45ffc60e4008d"
        }
      ],
      "codeRepository": "https://github.com/casys-kaist/LLMServingSim",
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 3
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Infrastructure Simulation"
        }
      ]
    },
    {
      "@type": "SoftwareSourceCode",
      "@id": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure#software",
      "name": "LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure - Source Code",
      "description": "Develop a simulator to analyze and optimize heterogeneous and disaggregated serving infrastructures for large language models.",
      "codeRepository": "https://github.com/casys-kaist/LLMServingSim",
      "url": "https://github.com/casys-kaist/LLMServingSim"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Infrastructure Simulation",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "LLMServingSim 2.0: A Unified Simulator for Heterogeneous and",
          "item": "https://sciencetostartup.com/paper/llmservingsim-2-0-a-unified-simulator-for-heterogeneous-and-disaggregated-llm-serving-infrastructure"
        }
      ]
    }
  ]
}

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(58)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(58)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline