Pith. sign in

Paper Citation Record Β· LEDGER

Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control

As of 9 August 2026, this Paper Citation Record lists 3 of 3 outbound references and 4 inbound Pith citation observations for arXiv:2602.02987.

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

pith.paper-citation-record.v1
2602.02987 v2

Coverage vector

measured 3 of 3 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:15:42.040300Z

measured 7 of 7 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:31:29.232092Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T08:55:35.093567Z

Reference resolution

3 of 3 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved3
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a0acc500-e879-4e94-a18a-2628fd1df0df Β· outbound

This paper cites Ai R, Pan Y, Simchi-Levi D, Tambe M, Xu H (2025) Beyond majority voting: LLM aggregation by leveraging higher-order information.

Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control Ai R, Pan Y, Simchi-Levi D, Tambe M, Xu H (2025) Beyond majority voting: LLM aggregation by leveraging higher-order information

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-03T05:15:41.857474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T05:15:41.857474Z digest=sha256:d9f8bcc15d427f8d999dcc986c39b9f5b6388e27c07dd3bf543e80a28ffd9fa7

Observation 7ce7a5c9-10d0-4715-9235-844db08ee641 Β· outbound

This paper cites Since𝑦 𝑠,𝑖(𝑑)→𝑦 β˜… 𝑠,𝑖 and𝑦 π‘š,𝑖(𝑑)→𝑦 β˜… π‘š,𝑖, the pool-level LP balances satisfy 𝑝𝑠,π‘–πœ‡π‘,𝑖π‘₯β˜… π‘–βˆ’πœ‡π‘ ,π‘–π‘¦β˜… 𝑠,𝑖=πœƒπ‘–π‘žβ˜… 𝑑,𝑠,𝑖,(1βˆ’π‘ 𝑠,𝑖)πœ‡π‘,𝑖π‘₯β˜… π‘–βˆ’πœ‡π‘š,π‘–π‘¦β˜… π‘š,𝑖=πœƒπ‘–π‘žβ˜… 𝑑,π‘š,𝑖.

Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control Since𝑦 𝑠,𝑖(𝑑)→𝑦 β˜… 𝑠,𝑖 and𝑦 π‘š,𝑖(𝑑)→𝑦 β˜… π‘š,𝑖, the pool-level LP balances satisfy 𝑝𝑠,π‘–πœ‡π‘,𝑖π‘₯β˜… π‘–βˆ’πœ‡π‘ ,π‘–π‘¦β˜… 𝑠,𝑖=πœƒπ‘–π‘žβ˜… 𝑑,𝑠,𝑖,(1βˆ’π‘ 𝑠,𝑖)πœ‡π‘,𝑖π‘₯β˜… π‘–βˆ’πœ‡π‘š,π‘–π‘¦β˜… π‘š,𝑖=πœƒπ‘–π‘žβ˜… 𝑑,π‘š,𝑖

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-03T05:15:42.040300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T05:15:42.040300Z digest=sha256:f142e5f5af83af671768720ec2ddd1bac15c291f6cec2d21c111cd2440dcf4bd

Observation 9d61e3fd-b5a2-45cb-afd7-64a69c392c9c Β· outbound

This paper cites Adaptively Robust LLM Inference Optimization under Prediction Uncertainty.

Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control Adaptively Robust LLM Inference Optimization under Prediction Uncertainty

Reference 2147

Resolution
unresolved
no resolver link, observed 2026-08-03T05:15:41.936426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T05:15:41.936426Z digest=sha256:6247937dff1b554a388e9b99a710f0ba65e3f837432ff4cf4137157dbca573e0

Pith citing papers

Observation ca0faaad-4eca-4e7a-9d2d-9941f10e71ab Β· inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control

Reference 47

Resolution
verified exact
local_arxiv, observed 2026-06-30T14:04:45.281734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-30T05:37:13.211613Z digest=sha256:c3cde0007c437e7aef37868c0929b1ef8e3a43b1748e95b7dd76cc46ac5e4234

Observation 97f7bde6-736a-4574-bab8-53013be9c952 Β· inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control

Reference 47

Resolution
verified exact
local_arxiv, observed 2026-07-01T08:55:35.095534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-07-01T07:06:53.318182Z digest=sha256:611b446b3a8c2158629863ac9f65d386f36cc76de2b86863f67f028a705e728f

Observation 6c4b8a25-23f2-403d-996a-a9294bf5cff8 Β· inbound

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving cites this paper.

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-14T01:11:57.017686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T01:11:57.017686Z digest=sha256:d7db77f2821b83ef475a2657406cbdade431366fa2c1d605757c77c00784f17a

Observation bb72724a-c6e4-45f5-a5be-48031c84b077 Β· inbound

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving cites this paper.

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T07:31:29.232092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T07:31:29.232092Z digest=sha256:28c33e297129750b0205908d70a6d5f0791dd0b6a823b548b646601f5e039cb6