Pith. sign in

Paper Citation Record · LEDGER

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference

As of 9 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2506.22033.

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

pith.paper-citation-record.v1
2506.22033 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:21:08.635007Z

measured 52 of 52 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

52 of 52 outbound references displayed

  • verified exact3
  • verified fuzzy5
  • unresolved43
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eda8f667-6c97-40e1-8709-c7640524db87 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:12.863562Z

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=2026-08-06T22:20:14.448663Z digest=sha256:1df595ffc67e7fba41b1dea27f14e9b29f85b380e3b07baad76511b482e2c05b

Observation a7e2ca0d-ed95-45fc-abf6-f24ce6039877 · outbound

This paper cites Llama 2 follow-up: too much RLHF, GPU sizing, technical details.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Llama 2 follow-up: too much RLHF, GPU sizing, technical details

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T22:21:12.743116Z

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=2026-08-06T22:20:14.523091Z digest=sha256:8f40be32f075d709ca1bea4489a73900627eb5520928d32040dbeab5c2990aad

Observation 27287006-71ea-4b4f-aee3-782b6863c827 · outbound

This paper cites AI Inference Market Size, Share and Trends Report.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference AI Inference Market Size, Share and Trends Report

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T22:21:12.550883Z

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=2026-08-06T22:20:14.589199Z digest=sha256:d49e1174ad694ffe493c1229528281edc7dfdcda898f8396e351dfb30eaa44b4

Observation 68c9c1f6-c288-418c-85e0-dbd25802cb0b · outbound

This paper cites OpenAI API Documentation.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference OpenAI API Documentation

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T22:21:12.301445Z

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=2026-08-06T22:20:14.662099Z digest=sha256:337df8ffda433aeba427551b2e50b876eab289eefa9859ec8059f01b7d1b6f1d

Observation 668572f2-9761-4394-81f0-0ed57fa41f2e · outbound

This paper cites ShareGPT Datasets.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference ShareGPT Datasets

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T22:21:12.099360Z

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=2026-08-06T22:20:14.755064Z digest=sha256:77e0c2d678241f78a7c92a02fc4e8767d79d4f6d0437779ad1d52b4a22bf6839

Observation 8fe31ad3-be65-41c5-9159-e878d7be02f9 · outbound

This paper cites vLLM–Optimization and Tuning.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference vLLM–Optimization and Tuning

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T22:21:11.863187Z

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=2026-08-06T22:20:14.834539Z digest=sha256:6a4a68a97b2a67ee3cc39b23a49d73d0c8f2c9bd7d57b93854c1360982e2ae92

Observation 4deeb3c9-ff8b-430a-8f4c-eb8486bcac22 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.726600Z

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=2026-08-06T22:20:14.945681Z digest=sha256:b5db56a9464b87cf5f11a0bac46941b4f3de5fc5999438634d61bf68f86e0d40

Observation 483eb470-30d0-4c87-96da-62ab4b519120 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.584750Z

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=2026-08-06T22:20:15.016310Z digest=sha256:1396b54032622a754969f4d8ebbd1ca6517c949b68975bb9c2f0c6887e87ab96

Observation e3094ddb-046f-4c7f-ad34-77e5c2a2f2e9 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.432438Z

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=2026-08-06T22:20:15.106452Z digest=sha256:29a6495a2233e2508f760b5136856088842902eadd9f5011aa635a08f6835a69

Observation 8640ffa2-d7a3-4b79-abce-c8e5e86284ec · outbound

This paper cites Efficient Training of Language Models to Fill in the Middle.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Efficient Training of Language Models to Fill in the Middle

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:15.212688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:15.212688Z digest=sha256:e85c8af5260d8dc5dbf7979daf1fb09a46eb0caeb7e07d7b6f7aa17bff5f4623

Observation 28b0a20a-608e-4a84-b9cd-64802d1e956d · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.349478Z

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=2026-08-06T22:20:15.362759Z digest=sha256:d0d2c1467389db85c87592cb98a289b12e69cef860091b7d817f5013481a31a4

Observation 4c9d6a34-cb93-46be-b390-3dbaeabb0195 · outbound

This paper cites Hilfer fractional advection-diffusion equations with power-law initial condition; a Numerical study using variational iteration method.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Hilfer fractional advection-diffusion equations with power-law initial condition; a Numerical study using variational iteration method

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:15.500147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:15.500147Z digest=sha256:6ed7af2cfbd597ca62474019460ad17747a45ce9055addd2170348c0f18cf46c

Observation 350d479b-3d67-42c8-930c-01e10176205f · outbound

This paper cites Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism

Reference 13

Resolution
verified exact
local_arxiv, observed 2026-08-06T22:21:09.451557Z

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=2026-08-06T22:20:15.603651Z digest=sha256:58ab9cdd1131668ddc91b08da6a63e7bd388ae0d3913bc856e56bdf237f7d30d

Observation cf1e1b8c-182c-4363-b042-b7af0fc35e48 · outbound

This paper cites The Llama 3 Herd of Models.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference The Llama 3 Herd of Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:15.704474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:15.704474Z digest=sha256:9f8c7a647749ac5c3c2f56aa69368e41792ff682c2cc752ef8d6f6bfdb5bd279

Observation 69d42e74-a598-4bce-8b85-3f8147ce0421 · outbound

This paper cites Hierarchical Neural Story Generation.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Hierarchical Neural Story Generation

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:15.795643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:15.795643Z digest=sha256:5f541a2156d8a5c17d1acce936c66fc9bc29802b671ae44d0991985199936d17

Observation d82b7fb0-3dec-4317-b55d-62d7d524cea7 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.240085Z

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=2026-08-06T22:20:15.876134Z digest=sha256:9bbc10a245dba1914425954a95f49dc6a0f0cc9caf77d5ed319e45623263c35e

Observation 67316e09-607d-48a7-82e8-eaf985ffa864 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:15.954063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:15.954063Z digest=sha256:6423c4a4600bf547abbce8a2a2f17f1751e1af01ef8ee4712508bbdc4af71602

Observation f4f58a12-cd6b-4257-af48-4a0438e3610e · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.143841Z

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=2026-08-06T22:20:15.998595Z digest=sha256:884729b746b4c0fbcaa37ab43d7cc472129155766bb86ffe01d2cf3a1ee96472

Observation afe2f31d-fd0a-4e3f-a1af-958f0bfb29db · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.049548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.049548Z digest=sha256:8b6bba36a85a25fbe8a4a3ac47aae50c0411e8a1c0d63f4492ababc0ce21e8a6

Observation 7bbfbc50-d118-4b34-af80-607e28c5d775 · outbound

This paper cites gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling

Reference 20

Resolution
verified exact
local_arxiv, observed 2026-08-06T22:21:09.287877Z

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=2026-08-06T22:20:16.114739Z digest=sha256:0ffa33d2f1b0ebe098fd0c37307d916a35f403970bb597ccc835cc63fdac8259

Observation 89a8467e-b453-40b8-8e93-3be55432743c · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.190154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.190154Z digest=sha256:898b0448fe8c4c17c40db69b22037d986b230d885dc4e3674686fef5a5a058ff

Observation 63992c81-8c65-4d35-a313-9d211d0648ff · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:11.024519Z

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=2026-08-06T22:20:16.258548Z digest=sha256:28976c445eb6962309def88e22fe29f9e648cb000bae71bd077717839b06f4a9

Observation 629b038b-6b07-410a-a29f-4922ae16be94 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.342358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.342358Z digest=sha256:27f917de78976e134f9367d48fd0d71b8147948da2ae922a8b7bcf5dfb72e9e3

Observation d12dede5-368d-42b3-85a1-9949a2573ab1 · outbound

This paper cites Mixtral of Experts.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Mixtral of Experts

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.520554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.520554Z digest=sha256:20294755821692ea90deb14593d9b3f23b1c789a9ef5fb9bd114023a22d7dbe6

Observation 16e3a6c2-f9b7-4c5e-94b9-2c95b6aa4ea8 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.614495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.614495Z digest=sha256:f02a61fce8a46ed1d106fb288378b9ca3262cc75e9882ca2b217c4c9e083ad45

Observation 5d084f37-96ae-4aa0-be5d-434df4b4cf17 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.930151Z

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=2026-08-06T22:20:16.667095Z digest=sha256:e93aef7f9c6117b22dfafb6ff8e12f5ee0f11ee7e6bc4d651c53a1d5110ffbe4

Observation 0c7059ae-fd6d-4c0f-b1ea-c9eb65dbaa9b · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.881512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.881512Z digest=sha256:9aa6e81a1f4debc4050fc458a997371ac7210b3f47a8a3c24b12d867cd6b4ec4

Observation b96b25f9-5721-49c1-8109-4d4a7e9ff94a · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 28

Resolution
verified exact
raw_fallback, observed 2026-08-06T22:21:09.118369Z

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=2026-08-06T22:21:07.644237Z digest=sha256:06c3b4b999451a527876dacdfd216149ad2a96d4e5be25bea1ef280ddd144838

Observation 7bc78cbf-e16f-4e8b-af8b-44bacdcbc419 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.784355Z

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=2026-08-06T22:21:07.727480Z digest=sha256:05c948017bcc73b160a2bc10f8e0a14a8c1b48bbdc5d84b5fc6b73796f1b1f1a

Observation 5508d0a2-44cb-4a0c-8501-fa58a3e1ab7e · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:07.812287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:07.812287Z digest=sha256:edcb74ad6efdfa76f8cf947cf1fff41ce277cf2cac7ce645f10c5c390e4e545c

Observation ae5d44d4-a143-4a01-a804-ee47ff718c66 · outbound

This paper cites DeepSeek-V3 Technical Report.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference DeepSeek-V3 Technical Report

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:07.904773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:07.904773Z digest=sha256:770d7c3e281ccccbfa53de771ad9e05aeee75399ccb0ef17195d272a5e6997e9

Observation cefce2a6-b69d-41e6-8783-336b31613bd1 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 32

Resolution
malformed identifier
no resolver link, observed 2026-08-06T22:21:07.961712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:07.961712Z digest=sha256:03a72c5058cb9b31bb1b8d71d9197319ba5807ed11aa1fd9e99742c8ec6c1fd6

Observation 4310d535-db69-4f10-a7f5-da9604b867fb · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.709481Z

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=2026-08-06T22:21:07.985649Z digest=sha256:f8eaa2901afa650fb1eefcb74b714a4445e17f18dbd1d8fb5e593d17555dd3a7

Observation 0950a895-2307-4290-a159-804a45563232 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.588607Z

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=2026-08-06T22:21:08.079266Z digest=sha256:376acdd23e5cba86bb5430edd540f5f42e7d8daa105992f7e7df97471e402484

Observation 098aa4c5-edf9-4cd1-8311-560e59a21832 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.481868Z

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=2026-08-06T22:21:08.146466Z digest=sha256:a8f19fac10ca14ead8757c2b5cdf8cc611ee57e2d3c78816b106ebd318924013

Observation 23c3e4f1-55b1-48d2-b753-caa8000d3519 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.323146Z

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=2026-08-06T22:21:08.224850Z digest=sha256:767a213aa192dfa73b647dccc2b938073d5aa6a5467c4029cfacb6fb99447575

Observation 24a13c47-9d69-4473-9ce4-e6d805307483 · outbound

This paper cites The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.252474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.252474Z digest=sha256:86f97e64721efa0a816d30d13793831932d936d5ff6be241332c91021aad4ff1

Observation 19a82f40-f7bf-463a-890a-6dfa5ac806b5 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.232576Z

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=2026-08-06T22:21:08.291122Z digest=sha256:845a7e5205915034240d2e4c9760c84baddd32e82d8eb8120d843e155bde998b

Observation c531d65f-241c-49a2-b291-30be26f522f0 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 39

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.134845Z

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=2026-08-06T22:21:08.316471Z digest=sha256:bb8981442d70bb523ada927bd160a933e8cf65ccabbe737a85c73e24b744b1a5

Observation 1356f8a4-9c85-464a-9ac5-39522fae388a · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.334204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.334204Z digest=sha256:7e9be16e3258197c86c3c6b609591ffa52ea61fe88365e44bf93bac6ccca46d9

Observation 214c4e61-2956-459c-9afe-5f4bb09df192 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.365349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.365349Z digest=sha256:99fc6f5fe0483c67adf838636ca29ab036316aacd4291285f80d7f2a4f4eac75

Observation 5c9a273f-9b2b-41e0-b87c-de85b7be8551 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:10.025414Z

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=2026-08-06T22:21:08.404913Z digest=sha256:78d22a6f35fcff51d2891f1daaa2d1a762d2c432660644b0ca6f3d6b9ac5ed5c

Observation d9ca8580-08af-4309-a510-6bc2fdc74e20 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:09.862571Z

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=2026-08-06T22:21:08.433933Z digest=sha256:2458f13a8128d58dc2f32a4c13ac9d2e0bb86be34a5af3272b9ca4bae206a624

Observation 40d011e9-9cfc-47ad-a30a-8069b912bb21 · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.482407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.482407Z digest=sha256:6c918731cba5f2bd1545494bcc4aba0dd59d96a2ebc67b188476951a707b2bdd

Observation a0796d54-cf61-41e1-aefe-f2c49c2629a8 · outbound

This paper cites PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.502337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.502337Z digest=sha256:7a5efcf8c0595859e3d84e01225c180128d28b3dc83733d3b7ba17d2ddbba39b

Observation 0f81eb64-e1e7-4ed4-a5e1-54e3f4ad135b · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:09.707779Z

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=2026-08-06T22:21:08.511891Z digest=sha256:efa56bb54cfa640b37c161e193b1d56b643fb51bfde4576937fe3493bdf350ad

Observation 51b7d836-3419-4b09-8350-ea0d214bd869 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference SGLang: Efficient Execution of Structured Language Model Programs

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.549867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.549867Z digest=sha256:0aadc569d724ec61c73be0e31003b4f9fa3658273d8cf023629a6e8a892614f4

Observation 557c3af2-268f-4f09-8fc4-5c2d1f9749ec · outbound

This paper cites an unresolved cited work.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-06T22:21:09.605042Z

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=2026-08-06T22:21:08.587759Z digest=sha256:0bbcff41187bd86a7b7b79e1471e9b7c59fec8ac4d7d8852f5a7020706ce3ef0

Observation 9b514c71-d402-45ab-9f31-d839c8a7030d · outbound

This paper cites MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T22:21:08.635007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:21:08.635007Z digest=sha256:e93513b4f05edd2d2ed66009dfa9e58b9e84c94f21ae344938506b319a1b95b7

Observation 89d81ba5-9760-4bd5-ab5c-1ec0d6815487 · outbound

This paper cites Importance of Search and Evaluation Strategies in Neural Dialogue Modeling.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference Importance of Search and Evaluation Strategies in Neural Dialogue Modeling

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.776351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.776351Z digest=sha256:249d94827420e7d9b87c69cd01524c677e5f4f62ff5d71ea4df744733e34e2fa

Observation d990ec36-4a83-46ce-8f78-4998e8148b68 · outbound

This paper cites The Curious Case of Neural Text Degeneration.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference The Curious Case of Neural Text Degeneration

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.448376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.448376Z digest=sha256:55cf1c7425839a826644651622257c965b6b83ca108dc9df07f147b91a871baf

Observation 49db65b0-7641-43df-b475-86403e866d8c · outbound

This paper cites In Proceedings of the 29th Symposium on Operating Systems Principles.

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference In Proceedings of the 29th Symposium on Operating Systems Principles

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T22:20:16.951598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:20:16.951598Z digest=sha256:ffdae6104225249ef640d3c8f7a9ccd67087170135d294b8b3ec410c27a63bde

Pith citing papers

No inbound Pith citation observations are available.