Pith. sign in

Paper Citation Record · LEDGER

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism

As of 7 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 1 inbound Pith citation observation for arXiv:2509.08309.

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

pith.paper-citation-record.v1
2509.08309 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T20:53:34.066002Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T16:55:38.764173Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T17:02:24.553672Z

Reference resolution

53 of 53 outbound references displayed

  • verified exact1
  • verified fuzzy4
  • unresolved48
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 31875306-5efe-4012-9a2a-50618d5b531c · outbound

This paper cites NCCL: accelerated multi-GPU collective communication.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism NCCL: accelerated multi-GPU collective communication

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T20:53:37.756092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:30.541035Z digest=sha256:5555f96529811d4c9f5db5d244688bca55b5c30b8e53554c9b1e64a532b60982

Observation 314d7857-8f3c-45cc-8158-b5bf6eedde3a · outbound

This paper cites ShareGPT.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism ShareGPT

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T20:53:37.660572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:30.595124Z digest=sha256:0856c0a6da61ce91b2a2808ce650bc4264afc55a1543191ecd06b04a0c2ffd61

Observation 41584052-a921-4839-8e82-d17e38fcea85 · outbound

This paper cites GPT-4 Technical Report.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism GPT-4 Technical Report

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:30.671849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:30.671849Z digest=sha256:2c0fdc8f230bec6c6f688c4b042187492310108b790d0eb5079b2019714c9f28

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

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

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.

source=pdf_text observed=2026-08-04T20:53:30.772845Z digest=sha256:920e19f190fd32e79346ce83f4bfbed2240d84b1659fc303b99b6bb0cd208e0f

Observation 1863aa73-3f8a-40b5-a13b-626c4eba2caa · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:37.575686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:30.844502Z digest=sha256:6e460d44ae27fecca0d952aa3379375429bbd29f8f3276bf378909c64b2ce6f2

Observation fa23cd5c-5924-4ca4-9fa3-6bd67dbfc07b · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:37.454601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:30.953102Z digest=sha256:f48d1a99a43c676325e0e16185d77d6e46db85c432fea0136682cf8b199e0be8

Observation 8dd0b71f-7983-4b72-8380-9b0cc492b4ee · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.024369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.024369Z digest=sha256:283d7da38a3830a3fdaca21a65eb0f0652babe63f8bf3d88cf2f025d7e18e46a

Observation ba04eae8-0604-4ca9-a88f-d4458ffd1816 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.063237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.063237Z digest=sha256:34aa8a6ec06882c153352663e8fc331521bb07600f578e9aa8390c5954e37868

Observation 5767af28-784d-4a6a-a5b7-0d5c36264212 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:37.344324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.134404Z digest=sha256:28ea936767f8b01a484f0f98545a523afbbf133099ed8ec365eb8989faba7717

Observation 51c3b14e-9f9a-4884-8d31-f9d5715d7568 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Evaluating Large Language Models Trained on Code

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.189865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.189865Z digest=sha256:cc2da7eaf9dbdb0b08806674ec614307f6f116f5c436492e095aa047028d39a1

Observation 368ee591-7614-4a19-9f1b-ecba55b6c56c · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:37.178582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.258524Z digest=sha256:2b3510deab71f1f195290bed5cbc75e9a54479c568b403f3ee74bca94c286b32

Observation c6c10d33-4c23-45a4-9b59-a668c1319ea9 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:37.090093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.342315Z digest=sha256:491bd83a4305737ad61e82f465aaec57018b50628c59889d97f382d0ddc40765

Observation d50ab370-f241-4da0-a763-77872ae9e7c8 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.403578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.403578Z digest=sha256:de7f59e2b84ce2015459134e937eb647cf51258e4e9866ce5cfdd11348990ad8

Observation 7b65c049-19e5-40e2-be0c-6fe88f51a563 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.961554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.462940Z digest=sha256:e36edb064944830d921a2ff341cca435defd8df000b9261537d107d37f497df1

Observation 4b67af20-9e6e-4f06-b9d2-dfc50e67c675 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 15

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.836867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.542101Z digest=sha256:be4d862e447afb2e0789178fc730ba1c3050902d3a94306b73f2f376e868f426

Observation c6d2838c-0aa1-4ac1-a702-220978ae3875 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.769021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.616944Z digest=sha256:f2fed9cbd068c8bd4cb0dad754fff0f651268a6697f70fcaa513542ad1945a71

Observation 8e3d6901-d154-496e-8359-f7975f57057b · outbound

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

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.694454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.694454Z digest=sha256:011d481bec29469174707c5856e463ba512aee5c61d5c0c57fa97a9fde169090

Observation fb76c67a-a3bd-4a00-8f44-7e60074990db · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.667598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.733099Z digest=sha256:2a52dedf7dd1a10df548ff71045c4f655ec7cd4a8bf382f2cb0c2faa6bc20476

Observation 3e8225a2-deb0-4c9f-b07a-c421677e2b82 · outbound

This paper cites FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.847951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.847951Z digest=sha256:cde397d52a9e1bbc676f88eed4c66750967f91a92a8667f3e6f23aadd4c5ee82

Observation 1f96ef1a-0a70-4f5b-96ed-3cd4aff33490 · outbound

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

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:31.939770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:31.939770Z digest=sha256:d8faae2b5e54bcf98c94400ab1378346a8af24421c411e19b89bca4962fc815a

Observation 4b0a3e99-b266-44b6-a4a1-79e02060586d · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.463932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:31.975896Z digest=sha256:df8fb31874b508594c52c1096ab962b9666abeb3e626cee05837b4db7207939e

Observation 5e9d1c0e-bfc9-4061-9951-c827e77c27b1 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.298639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.027110Z digest=sha256:f46955a9b3cbed40dd50940dee8e3c0963a023cb3e96cf36b6a86678af490d9b

Observation 3d92674d-fe92-4eb4-b448-ce72ff3e2b20 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:36.224438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.088532Z digest=sha256:b83b9caf0f82150c0135f6a92a3275ff0a0a3d80bfcdb996ca7cd80d6e893646

Observation b686db21-843e-411f-8a6c-c8487b734e0e · outbound

This paper cites Scaling Laws for Neural Language Models.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Scaling Laws for Neural Language Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.137323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.137323Z digest=sha256:c32515ca9fe16efc9ffb0e89abacb219f8d5e3af58c6488c7cf1856d6438e58d

Observation 6fb39267-e2b4-4deb-90a5-527f58a0a076 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.178971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.178971Z digest=sha256:27fe879ff7068f5dc1adc12c4ebefa9c1138218beb0e6a2ca8aecff5e1719d78

Observation 23e4405d-4b2d-428c-968d-51f0a60d82f1 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.915257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.267712Z digest=sha256:fb6bef0fed0f188cbce4fb35550b2350e874326acf15eda86ebfa378186387a7

Observation da68e34e-dd69-442d-80c7-d32975ea42b2 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.813704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.322858Z digest=sha256:caeb26caf34c2928eb120e67b401335d3e5a4906bb9dea1d1078ae92a4aa08ad

Observation 9bb1337b-8b54-4029-a2da-6816ad942ff8 · outbound

This paper cites Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.388187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.388187Z digest=sha256:5cac9b5231fb3d1c8cbaa6529fe27c5ed6424a88acf78be01b0440c90709e2b8

Observation 976d2ac0-de8a-4365-a28a-009492e9e362 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.726862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.491483Z digest=sha256:6627f7e56f4ac7300e5a8b12fde70f561a6fe8709ec8dcf8803d861a417a86a6

Observation 3dff3f13-9541-48f8-b411-ba022122b361 · outbound

This paper cites SpotServe: Serving Generative Large Language Models on Preemptible Instances.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism SpotServe: Serving Generative Large Language Models on Preemptible Instances

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.528246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.528246Z digest=sha256:cd14eef4e67727cbbc19ba57c8975be1075ec16f6059e5d0a6e78ed62ac17216

Observation 4bf2362f-a818-490f-a10b-8b59998f0b5c · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 31

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.608634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.597113Z digest=sha256:cf480f94c020a355ab5e666afa2ac2394877a6858ffef4d78aec879e872927b8

Observation b9e7bb2d-d007-4a9f-8803-2415067f8a44 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 32

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.508255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.674293Z digest=sha256:37d5520f85f025be8b63c341bd3020b82d2237c5f430608edd5f03a769d79692

Observation 5a22e5ab-74df-420a-a350-74313159d58f · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.431599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.700047Z digest=sha256:fb98252d75a547b9441490ebc7c2919224d4bd80878e569881edc86248196bd2

Observation f6ef0f0f-0b2e-43ee-a0be-3d6b451b1c9f · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.276426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.817436Z digest=sha256:4c3487acd407b07187ebea92dca3e6be3574512a5e9adf3dc9b91724b18818b1

Observation 2c772b5a-3f88-47a7-a971-2b7825104d01 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.888698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.888698Z digest=sha256:a1f6ed169244751f2999feed24661990eff47ef01288330863f371ccad1fc8e9

Observation 329816e1-9715-4379-9556-2f2cbb18c181 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:32.916183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:32.916183Z digest=sha256:50afba12d88860d505b288335b74b602a764753abf975e10c5636e59219bb6f4

Observation ac292109-23c6-468f-81f4-1390387279a7 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 37

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.140565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.957225Z digest=sha256:f9baadb748d97b415a965e9f9383fd566b51a62b88c8afb3b28f84bb8e587b7d

Observation ddbbc322-4944-47ae-b67a-0857d2d3be03 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:35.058157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.977810Z digest=sha256:4216305a1bc6baf8df31fe6400224d9821eafe4bf266dfe4db6a8a5b7b6f97a5

Observation 6095cc65-e929-4bb1-b1df-77ddac29c952 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:33.021674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:33.021674Z digest=sha256:0a6ddda825525eaeef82e14ea7e140088674caa563f3264fe102e2ef3abd0217

Observation dbb5ef4c-8faa-46a7-8869-978d9decfa69 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism LLaMA: Open and Efficient Foundation Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:33.067355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:33.067355Z digest=sha256:38adc58e347c17931cfbe66196689e5415738fd62cc347221e4d7166605772d9

Observation d986cac6-56e8-4fa6-8c8c-03a1c64b43e9 · outbound

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

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:33.187123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:33.187123Z digest=sha256:a0fbd8cf6cf7eb4d7c56d93527ca139454542556d8c095303604ef548721633a

Observation df5b6a15-9425-4f83-8a43-786069b96793 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:34.914683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.254465Z digest=sha256:df6d21ad4b9735601e725b716aa82cfebe3e1086213903bcafd8fb1944dcdb75

Observation 666ffacb-090f-433a-a9cd-74d0f8055985 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:33.343697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:33.343697Z digest=sha256:ca529f57f8d1247822e021f4e84c22b1d0a83622c6812bc8db22cd0196acc19c

Observation cf06d08f-ec08-47af-8b66-4e8f0b46a461 · outbound

This paper cites BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:33.420816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:33.420816Z digest=sha256:33aab6ee36947e50a9f239ea0759872bebe3edec92a44437da8ff3f0a9fbf0b2

Observation b93ecd0e-6ae3-406e-b1c5-8e65fcc55fc2 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:34.803025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.499490Z digest=sha256:0cad8609359a689668bbdce480dfaa4047c3659cbcf4403d0ce103871f11ddad

Observation 21f0cf2c-fd3a-40a0-8285-e4ed8df6999f · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:34.730050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.639354Z digest=sha256:54a58b263a523d28c4e1c242b41276785614ce7cc7cfe15fd2d0e023b7b2769a

Observation ec765750-2bd0-4111-9c42-1b624fd7f144 · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 47

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:34.626700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.771263Z digest=sha256:5da458e2027e5ca8e6237c6f80975fe4d1edca2b478877e3fd933a0a9d902de3

Observation c083b2f6-9138-4ff6-bfc9-eaafe3d262fc · outbound

This paper cites an unresolved cited work.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-04T20:53:34.505073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.845686Z digest=sha256:642c47512ff2b9e19c038e2198fcc7d0ce84dbcf49547e66532a674dfe798bda

Observation 12c864f5-7e26-470e-a535-741ec6502ec5 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism OPT: Open Pre-trained Transformer Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:34.002850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:34.002850Z digest=sha256:6f98f0b093f28b2ae0dd0119b647f55aab78bad8a06ec55b4536a6cac60fdca4

Observation 6f810480-b13f-4aa8-a392-a9be854e583b · outbound

This paper cites InProceedings of the Nineteenth European Conference on Computer Systems.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism InProceedings of the Nineteenth European Conference on Computer Systems

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T20:53:34.396862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:33.927177Z digest=sha256:ed1bed208f67ce0db3a4608d9564bd78b0fb1eadc3843d36e9c9ba44164eb57a

Observation 9192a142-3d6c-4fce-86d3-d76f90c84f91 · outbound

This paper cites DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T20:53:34.066002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:53:34.066002Z digest=sha256:2a0f8d623bc3ca13dc478769808b454336d79010c188deed7d0c9e207dd2cd9d

Observation 1348a3f9-69bb-46ae-9f58-35a695b08b7d · outbound

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

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization

Reference 52

Resolution
verified exact
local_arxiv, observed 2026-08-04T20:53:34.170416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:34.032926Z digest=sha256:4a421f62b415e875e5883420bacdd1f98ede0a535cc5d1826c21c770ae7b1caa

Observation 08cad4e3-d216-4e00-b78e-5da19ee5768e · outbound

This paper cites InForty-first International Conference on Machine Learning.

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism InForty-first International Conference on Machine Learning

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T20:53:36.130334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-04T20:53:32.113597Z digest=sha256:8ea984f5d4513bec6cce475d3dd9ada21f8ef435f7b6e1663123828443bf388d

Pith citing papers

Observation 38e3bb4d-7a66-4493-afca-66643d3f92db · inbound

Lodestar: An Online-Learning LLM Inference Router cites this paper.

Lodestar: An Online-Learning LLM Inference Router Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism

Reference 59

Resolution
verified exact
arxiv_id, observed 2026-06-28T17:02:24.555133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-06-28T16:55:38.764173Z digest=sha256:caf47fc2df267a2179eee2dffa79c99a8b8bb6131a1d44b2faa70577e5fff304