Paper Citation Record · LEDGER

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2403.02310.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2403.02310 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 31 of 31 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T20:53:30.772845Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

15
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 8f3425e2-02d2-4560-9573-4846b10184c5 · inbound

A Survey on Efficient Inference for Large Language Models cites this paper.

A Survey on Efficient Inference for Large Language Models Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 283

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:39:33.509031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1e99bc29-4825-41dc-bf6e-482fac912f0b · inbound

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production cites this paper.

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:44:58.114111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b80e34f7-c743-48f1-a56a-f98d807df92c · inbound

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism cites this paper.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T20:53:30.772845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a28d3b4-f021-4bb3-b926-0ec0c9ee9ddc · inbound

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators cites this paper.

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:58:42.965092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 97bcbd00-63ac-4df6-83be-2e57677b482c · inbound

PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction cites this paper.

PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:47:54.091286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c0e65acb-5eca-404e-823f-06ae489253f3 · inbound

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling cites this paper.

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:36:36.672643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9aa1a6b3-df44-4281-9401-d6426f28a503 · inbound

Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing cites this paper.

Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-09T00:34:30.279799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 43579636-675c-44d7-b5d5-786a088a8e5c · inbound

Agentic AI Systems Should Be Designed as Marginal Token Allocators cites this paper.

Agentic AI Systems Should Be Designed as Marginal Token Allocators Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:46:05.704482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 01a9a38f-abc6-4197-a51c-c117f799eff8 · inbound

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation cites this paper.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T02:45:58.613756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 74d58261-838b-4fd0-808d-b7d5c2fa05f4 · inbound

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation cites this paper.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.908790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dab488d6-f358-4543-9ec7-46d02a4c250b · inbound

Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design cites this paper.

Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T13:03:17.881842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9fce4adf-ae6f-4a6d-a3a4-4ef3950b03fc · inbound

HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools cites this paper.

HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:24:38.270384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bd969b09-0574-4b31-9ffa-01e9be155afa · inbound

DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving cites this paper.

DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-29T20:53:57.624787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3748cd8c-fe39-488d-b958-23b9b146be6f · inbound

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving cites this paper.

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:03:47.840958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ea36a92f-e078-4765-92ad-07ed17376370 · inbound

ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving cites this paper.

ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:46:13.223881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f3070805-629f-4d65-ac3a-4b88cb3866ef · inbound

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents cites this paper.

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:36:59.461051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f11ace76-a222-43e0-a171-c74632f0b438 · inbound

Beyond Prediction: Tail-Aware Scheduling for LLM Inference cites this paper.

Beyond Prediction: Tail-Aware Scheduling for LLM Inference Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:58:57.825283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2ca9d91d-efa0-46a4-826a-af33269b5ace · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 183

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T05:09:36.881011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67cb0682-5fcb-49f9-9ace-d0fb8fe0be3c · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 183

Resolution: unresolved; no resolver link, observed 2026-08-02T10:49:20.252837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd03649a-e348-4420-b995-3264601b0d54 · inbound

Load Testing for Machine Learning Model Serving Systems at Scale cites this paper.

Load Testing for Machine Learning Model Serving Systems at Scale Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T08:19:44.171292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c478561c-37b0-40dd-88e9-9e9473efcb13 · inbound

Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion cites this paper.

Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:59:58.321693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0970c22c-a640-4754-a322-26d9829e9c6c · inbound

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs cites this paper.

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:07:23.420190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cb35a35e-61eb-43a1-8743-61017d6e8f5e · inbound

KernelSight-LM: A Kernel-Level LLM Inference Simulator cites this paper.

KernelSight-LM: A Kernel-Level LLM Inference Simulator Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:54:06.298161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c25b08c1-89d8-4736-af91-0e1d640d5bc4 · inbound

KernelSight-LM: A Kernel-Level LLM Inference Simulator cites this paper.

KernelSight-LM: A Kernel-Level LLM Inference Simulator Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T23:19:02.267496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d2306179-367e-4b31-a14f-2eea20d99c93 · inbound

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference cites this paper.

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-01T11:35:43.651571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c37c6f3-b581-4bfd-aa59-fab3fe947a51 · inbound

OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters cites this paper.

OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T06:37:42.164177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fbfecaf3-58cc-4976-a941-5373c19bff38 · inbound

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes cites this paper.

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T15:30:19.741437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ddf9c1-8738-4d6a-a367-f9c2f8226ff3 · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:45:40.096209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bfd610e5-6faf-4584-9844-83ca056397f3 · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-11T01:57:51.380223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b7863588-a8d2-43b4-8caf-9c84ee16a394 · inbound

Persistent Computational State: A Session-Centric Runtime for Generative World Models cites this paper.

Persistent Computational State: A Session-Centric Runtime for Generative World Models Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:26.617631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46da00a1-c551-488c-8393-79b665384216 · inbound

Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling cites this paper.

Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T10:54:00.179459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.