Paper Citation Record · LEDGER

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference

As of 21 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 1 inbound Pith citation observation for arXiv:2501.11779.

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

pith.paper-citation-record.v1
2501.11779 v2

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T18:01:46.443737Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T10:07:06.141581Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T10:13:17.805330Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy3
unresolved62
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cd8de5fb-360c-4b60-9eb0-a7750f47ec22 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.812432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9afcc265-6c9e-493f-b264-bc249066982e · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.797233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b17145cb-ea74-4204-b576-b5c5fa1b91f1 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.782633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 40834a54-9776-447b-9d81-0578cc68fa6c · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.764911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5476b1d9-7ca1-40a4-a9fc-ce9d313715b6 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.749908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 32ae0556-c6f6-4648-9fc9-bef2c07adc3f · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.732416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 185deb44-aa19-4381-b0c9-6c2c9ad6812b · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.715213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d6f5c94e-829c-40e4-b784-ebd37a967a15 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.698905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5a96ce76-ce01-404f-91b7-de152b17b688 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.680983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 49fd9485-fe74-4915-ab5c-509fc4535d98 · outbound

This paper cites IEEE Standard for Floating-Point Arithmetic.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference IEEE Standard for Floating-Point Arithmetic

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.186890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30508ef3-964c-4a89-b862-55a835c64b15 · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.191693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b852a1a-d85d-48e5-ac61-781431ef0e37 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.196980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d873e317-48e0-4e95-9548-57e999c07e5a · outbound

This paper cites DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.202032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b10e56c-ab3a-48e8-8081-68882a03d8eb · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.664194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 821c8ffe-0d58-480e-ad1a-3e3f0e051c72 · outbound

This paper cites Language Models are Few-Shot Learners.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Language Models are Few-Shot Learners

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.216356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b0f0fc0-f990-4b19-974a-1ff4ed8a7f96 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.221091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc4d592-14b0-4872-b016-572b6b7205cb · outbound

This paper cites Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.225490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e3309a-8922-4408-8530-5963028a63ff · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Gonzalez, Ion Stoica, and Eric P

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:01:47.647618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f7acc176-41e2-4c67-900c-1bfb10329ef2 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.234652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0020f9a-f8d6-4595-8b60-7ddc5010b49c · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.239316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa93b2c9-582e-40a1-a862-d63a7b72ce3c · outbound

This paper cites The Llama 3 Herd of Models.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference The Llama 3 Herd of Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.247690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6de14574-7611-41a9-bc56-159929147cf3 · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.243579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df405801-7510-4393-ba9d-c170c58d0343 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.621766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 230a61d0-3247-457e-8bf9-041081624c0e · outbound

This paper cites A Review of Sparse Expert Models in Deep Learning.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference A Review of Sparse Expert Models in Deep Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.251978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5db946e-4b6a-4c3e-a57b-2ba309b685e3 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.606695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b71d3ac2-652b-4b38-bf8e-b82d796d912d · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.260751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7be11884-41b4-47eb-aaa8-98915c69c71e · outbound

This paper cites Hydragen: High-Throughput LLM Inference with Shared Prefixes.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Hydragen: High-Throughput LLM Inference with Shared Prefixes

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.274340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b7bc4e-ddf8-4658-af62-ab28c98b8f48 · outbound

This paper cites Mixtral of Experts.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Mixtral of Experts

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.269431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8976462-c76a-4b5f-abbb-98e1e5806d2d · outbound

This paper cites AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.288769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd323758-0973-4522-b625-69ca3526214e · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Gonzalez, Hao Zhang, and Ion Stoica

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.279142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0114ff0f-e917-4c51-826f-57473f90e5c3 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.298972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6f5535-8ba1-432d-8af5-80c971140973 · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.304481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa98683e-5b9a-43f0-a904-6183b0d6c34c · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.293818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee5166c2-c1a0-4b1c-adc1-74aa3e589515 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.313249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b20b16e-4b1b-4b6b-84d2-eeba8a108ed3 · outbound

This paper cites Can Foundation Models Wrangle Your Data?.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Can Foundation Models Wrangle Your Data?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.317445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6328fcdd-c8a6-4999-ae95-e56846b34da7 · outbound

This paper cites Very Deep Transformers for Neural Machine Translation.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Very Deep Transformers for Neural Machine Translation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.309018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe44fe3-76cd-49eb-aa0b-1d355d017a14 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.325426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77e6827-4ea1-4d3f-a9bc-6b04e3dcacaf · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.566549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a12cfd8b-e8f4-4433-b6db-008b8cc6c386 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.581844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d608c8dd-c737-4c05-acef-536a9115555d · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.551053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ed95a91c-db04-4f62-89b6-c23584fb5e00 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.342837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 008b4344-7dd3-45f0-807d-d483848decd0 · outbound

This paper cites Splitwise: Efficient generative LLM inference using phase splitting.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Splitwise: Efficient generative LLM inference using phase splitting

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.333688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09dea148-68ba-4b46-ab31-f4962826ad67 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.352066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a4d17f1-51ec-4698-af02-cf6ce691bef2 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.511723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8a63bae5-8be2-49fb-8f40-8dc294552bbb · outbound

This paper cites ZeRO: Memory Optimizations Toward Training Trillion Parameter Models.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference ZeRO: Memory Optimizations Toward Training Trillion Parameter Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.347288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3109990-33ca-4a29-8056-87fc6b526f6d · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.371711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 538f9376-388b-4a88-bd12-368ad2660701 · outbound

This paper cites FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.376642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddef0a13-13fc-4950-85de-3fddc4607b09 · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.381691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc9cdde-5e85-4042-8003-9455e23d8fd1 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Fast Transformer Decoding: One Write-Head is All You Need

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.366806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1388f066-5ab7-4032-800b-0946cd7feb8e · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Gemma: Open Models Based on Gemini Research and Technology

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.395770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e96f27-0529-4ed8-9291-2434bfab177a · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference LLaMA: Open and Efficient Foundation Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.400525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8075934-419a-4ff1-824a-69fc162d6966 · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.405679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b1b74c8-5585-4af5-9e9d-9f80e3477958 · outbound

This paper cites Hashimoto.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Hashimoto

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:01:47.495870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation aa9fc5da-241b-48a4-a391-f12f25d25746 · outbound

This paper cites https://github.com/tatsu-lab/stanford_alpaca.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference https://github.com/tatsu-lab/stanford_alpaca

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:01:47.480502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6638c6f8-f207-4fbc-9d19-e9a5194ea8a8 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Efficient Streaming Language Models with Attention Sinks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.419673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a341c62-7758-4ef6-9b7b-f3a906243954 · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.446422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ead83c85-b29d-4a54-8b74-e380f9d34488 · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.429279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e4e9b8-bffb-405d-a62d-5efe4dd4944f · outbound

This paper cites Attention Is All You Need.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Attention Is All You Need

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.410490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aac2e18-c272-4954-a29b-1199c8c3ddca · outbound

This paper cites an unresolved cited work.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:01:47.463238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6ae9f20-fcf8-4cfd-9b14-1d03b3498b32 · outbound

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

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference SGLang: Efficient Execution of Structured Language Model Programs

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.443737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78efc752-fb3c-448b-8aa0-b3c6f03409f4 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.434131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246c3827-a89b-4aa2-9451-d0bfe498b018 · outbound

This paper cites Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.438859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8781437-3a20-4210-8d3c-598c1a342079 · outbound

This paper cites ZeRO-Offload: Democratizing Billion-Scale Model Training.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference ZeRO-Offload: Democratizing Billion-Scale Model Training

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.357295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641f29ab-e41c-47fd-9499-c9961485dcc7 · outbound

This paper cites Petals: Collaborative Inference and Fine-tuning of Large Models.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Petals: Collaborative Inference and Fine-tuning of Large Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.211564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ea8d80-6826-4545-b75a-8d3a2f494986 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T18:01:46.284071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 92ab72be-fe40-44fe-beda-082c7f07b3c8 · inbound

SiDP: Memory-Efficient Data Parallelism for Offline LLM Inference cites this paper.

SiDP: Memory-Efficient Data Parallelism for Offline LLM Inference Glinthawk: A Two-Tiered Architecture for Offline LLM Inference

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T10:13:17.806801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.