Paper Citation Record · LEDGER

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 6 inbound Pith citation observations for arXiv:2502.07903.

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

pith.paper-citation-record.v1
2502.07903 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:32:21.565332Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T19:23:10.356881Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T02:39:25.561444Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy2
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b5cefa72-6c65-47b6-9438-289231eddfde · outbound

This paper cites Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.500409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 423abc3b-70e3-4084-8020-fa01aed8be71 · outbound

This paper cites Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.534466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79bed0e8-68bf-4c79-8f88-7801c21e777c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.538918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd71096-76f5-4be3-a0b4-44301976be9d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.544002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87f543d8-c790-49e1-ba96-7c5c0d3bdf2a · outbound

This paper cites Jintao Zhang, Jia Wei, Pengle Zhang, Jun Zhu, and Jianfei Chen.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Jintao Zhang, Jia Wei, Pengle Zhang, Jun Zhu, and Jianfei Chen

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.554868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3a00386-2e4a-4270-b859-6f0331b02722 · outbound

This paper cites LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.559881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd526f8-3ccf-484c-8d4e-4e9859f2fc5c · outbound

This paper cites {PetS}: A unified framework for {Parameter-Efficient} transformers serving.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment {PetS}: A unified framework for {Parameter-Efficient} transformers serving

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:32:21.981265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2285e570-6cee-4516-8a86-235903b03ff1 · outbound

This paper cites Fast Distributed Inference Serving for Large Language Models.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Fast Distributed Inference Serving for Large Language Models

Reference 1994

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.550145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f5124e-0c28-4768-96ea-f48d73ec1a13 · outbound

This paper cites Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Reference 1995

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.510038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f871e621-bd67-44ef-8d0c-a1b5ae884e5e · outbound

This paper cites Mixtral of Experts.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Mixtral of Experts

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.514573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a53e3198-57e8-440d-903e-54aa16bc353f · outbound

This paper cites M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.505463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3200e3ad-3931-4619-a58f-92ab2c9c5492 · outbound

This paper cites Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.524538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fed70cf4-1107-4109-992e-f6b781c62f4b · outbound

This paper cites 12 Pratyush Patel, Esha Choukse, Chaojie Zhang, Aashaka Shah, ´I˜nigo Goiri, Saeed Maleki, and Ri- cardo Bianchini.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment 12 Pratyush Patel, Esha Choukse, Chaojie Zhang, Aashaka Shah, ´I˜nigo Goiri, Saeed Maleki, and Ri- cardo Bianchini

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T11:32:21.994984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9669077d-a821-4144-b871-35e595bbefee · outbound

This paper cites P/D-Serve: Serving Disaggregated Large Language Model at Scale.

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment P/D-Serve: Serving Disaggregated Large Language Model at Scale

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T11:32:21.519527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f6af0e65-dc06-4bd5-a5a4-4f94f0c43ad5 · inbound

HexiScale: Facilitating Large Language Model Training over Heterogeneous Hardware cites this paper.

HexiScale: Facilitating Large Language Model Training over Heterogeneous Hardware HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.647282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 36654a16-284c-4825-bb95-a5e3912bb6d8 · inbound

Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics cites this paper.

Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:41:20.938460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a48c718a-0f5e-43f4-81d0-06a71f91a7b1 · inbound

Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation cites this paper.

Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:46:07.159142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 794abd5e-649c-49c7-a89f-20efa4d69804 · inbound

HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware cites this paper.

HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:00:55.538297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 35c006a8-a506-458e-acef-ad8a7a1fe53c · inbound

HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling cites this paper.

HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-19T21:02:47.427981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 04200cc2-3edc-4b7c-8fa8-1a9f54813cec · inbound

TurboServe: Serving Streaming Video Generation Efficiently and Economically cites this paper.

TurboServe: Serving Streaming Video Generation Efficiently and Economically HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:39:25.563163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.