Paper Citation Record · LEDGER

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

As of 5 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 60 inbound Pith citation observations for arXiv:2308.16369.

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

pith.paper-citation-record.v1
2308.16369 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T06:31:47.330226Z

measured 108 of 108 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 60 of 60 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T18:49:21.474198Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

48 of 48 outbound references displayed

verified exact3
verified fuzzy43
unresolved0
parse uncertain1
malformed identifier0
metadata mismatch1

External citation measurements

15
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a105e427-4160-4241-a2a1-abea7e724f96 · outbound

This paper cites https://aws.amazon.com/ codewhisperer/.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://aws.amazon.com/ codewhisperer/

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.522365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e902f87a-52a2-477f-b2db-bf0cb17a17d1 · outbound

This paper cites https://claude.ai.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://claude.ai

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.528671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f5824472-cfc1-4eaa-a535-a0a4fd72e88c · outbound

This paper cites https://www.bing.com/chat.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://www.bing.com/chat

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.531607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ef6b5aba-023a-4817-bfab-f635250e345c · outbound

This paper cites https://character.ai.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://character.ai

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.534417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 56523f58-fab0-4040-aba0-86d409455c8e · outbound

This paper cites https://chat.openai.com.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://chat.openai.com

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.387231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e3dd7e90-3bd7-42c4-aba1-130564e9b81b · outbound

This paper cites https://github.com/NVIDIA/ FasterTransformer.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://github.com/NVIDIA/ FasterTransformer

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.390775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 43b77621-ebaf-4d1e-b36f-2f25293ab284 · outbound

This paper cites https://github.com/features/ copilot.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://github.com/features/ copilot

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.393917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a0d36354-b63a-49a9-9f1d-e2ba054a5726 · outbound

This paper cites https://bard.google.com.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://bard.google.com

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.396924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8f3d80ce-3263-4912-b024-4ea163211f2d · outbound

This paper cites https://komo.ai/.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://komo.ai/

Reference 9

Resolution: parse uncertain; raw_fallback, observed 2026-05-16T06:31:47.400069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 39d7275e-1c3c-40f4-891d-4f19b6eb04f9 · outbound

This paper cites https://huggingface.co/ decapoda-research/llama-13b-hf.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://huggingface.co/ decapoda-research/llama-13b-hf

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.403590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a093a949-6477-47fb-a696-b07e3dd97d9e · outbound

This paper cites https://docs.nvidia.com/deeplearning/ performance/dl-performance-matrix- multiplication/index.html.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://docs.nvidia.com/deeplearning/ performance/dl-performance-matrix- multiplication/index.html

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.407072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6bde7ef6-0a05-4405-9d02-3e1d2b17f4d0 · outbound

This paper cites https://github.com/karpathy/nanoGPT.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://github.com/karpathy/nanoGPT

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.410143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 232a8aaf-560b-433e-a12c-5b90447c3ab3 · outbound

This paper cites https: //developer.nvidia.com/nvidia-triton- inference-server.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https: //developer.nvidia.com/nvidia-triton- inference-server

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.413152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 881f4fa7-d0ce-40f2-81cd-3e103c0997b8 · outbound

This paper cites https://www.theaidream.com/post/openai-gpt- 3-understanding-the-architecture.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://www.theaidream.com/post/openai-gpt- 3-understanding-the-architecture

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.416734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf913a27-8cc5-4926-9738-1286a09b353f · outbound

This paper cites https://www.perplexity.ai/.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://www.perplexity.ai/

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.420385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8beb3fb5-dab8-4427-abcc-cd05394948b4 · outbound

This paper cites https://replit.com/site/ ghostwriter.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://replit.com/site/ ghostwriter

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.425685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 766a7a7a-b3a2-44bc-abe2-146c818423af · outbound

This paper cites https://huggingface.co/ text-generation-inference.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://huggingface.co/ text-generation-inference

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.428812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d844abbd-a60c-4928-953c-92d11bd7164b · outbound

This paper cites https: //blog.gopenai.com/how-to-speed-up-llms- and-use-100k-context-window-all-tricks-in- one-place-ffd40577b4c.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https: //blog.gopenai.com/how-to-speed-up-llms- and-use-100k-context-window-all-tricks-in- one-place-ffd40577b4c

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.432185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 70ef3112-31bb-427e-a177-33cf0f40ad31 · outbound

This paper cites https: //core.vmware.com/blog/using-nvidias-aiml- frameworks-generative-ai-vmware-vsphere.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https: //core.vmware.com/blog/using-nvidias-aiml- frameworks-generative-ai-vmware-vsphere

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.435797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e290db03-dd13-44ba-83d3-f8f0d22b44a2 · outbound

This paper cites https://github.com/vllm-project/vllm.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://github.com/vllm-project/vllm

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.439266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57426900-144d-47fd-b70b-4beaf116d805 · outbound

This paper cites https://facebookresearch.github.io/xformers/ components/ops.html.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://facebookresearch.github.io/xformers/ components/ops.html

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.442729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b3108b96-2be2-4ef8-a367-7d3d33348065 · outbound

This paper cites https://you.com/.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills https://you.com/

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.445810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 46f32074-a200-4aa0-b324-b8e31b72980c · outbound

This paper cites Ef- ficient large scale language modeling with mixtures of experts.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Ef- ficient large scale language modeling with mixtures of experts

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.448872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 369ca656-70c0-469a-98cc-3e165495f53a · outbound

This paper cites Varuna: scal- able, low-cost training of massive deep learning models.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Varuna: scal- able, low-cost training of massive deep learning models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.451841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c134673a-3b18-404f-bd34-597431574682 · outbound

This paper cites Language models are few-shot learn- ers.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Language models are few-shot learn- ers

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.455157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b517b334-edd3-480e-992c-a8a2bb97ca17 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills PaLM: Scaling Language Modeling with Pathways

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:31:47.370660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1b9d845d-20b8-4a40-a068-9ae8477833d3 · outbound

This paper cites Clipper: 15 A {Low-Latency} online prediction serving system.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Clipper: 15 A {Low-Latency} online prediction serving system

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.458092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bffd7178-3a30-4336-84cb-641bfa3001d5 · outbound

This paper cites Flashattention-2: Faster attention with better parallelism and work partitioning.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Flashattention-2: Faster attention with better parallelism and work partitioning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.461983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78cb58de-9125-440b-8f0a-143734629bf6 · outbound

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

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.465251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 49d17720-2838-4863-96b5-484def4aff56 · outbound

This paper cites Llm.int8(): 8-bit matrix multiplication for transformers at scale.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Llm.int8(): 8-bit matrix multiplication for transformers at scale

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.469018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 95821179-3f0a-46cf-99c3-c3627a8a6e56 · outbound

This paper cites Qlora: Efficient finetuning of quan- tized llms.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Qlora: Efficient finetuning of quan- tized llms

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.472500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f7dc33df-c59a-41fb-b718-2479d2455d15 · outbound

This paper cites Gptq: Accurate post-training quantization for generative pre-trained transformers.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Gptq: Accurate post-training quantization for generative pre-trained transformers

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.476366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c1d80fe-473a-49b0-b9fa-b0bb66b0011c · outbound

This paper cites Lee, Anjali Sridhar, Shruti Bhosale, Carole-Jean Wu, and Benjamin Lee.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Lee, Anjali Sridhar, Shruti Bhosale, Carole-Jean Wu, and Benjamin Lee

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.479244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3aaddcb9-7463-4584-b7fa-8b24980c6c5c · outbound

This paper cites Gpipe: Effi- cient training of giant neural networks using pipeline parallelism.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Gpipe: Effi- cient training of giant neural networks using pipeline parallelism

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.483062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation df99e933-060a-4123-968b-bfe415ee2feb · outbound

This paper cites Scaling Laws for Neural Language Models.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Scaling Laws for Neural Language Models

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T06:31:47.383653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 91b23fbd-e8cd-4d7b-bc13-55e0957c0490 · outbound

This paper cites Accelerating distributed MoE training and inference with lina.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Accelerating distributed MoE training and inference with lina

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.486920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4998e0ee-cb84-48de-ac81-d8c86618bc94 · outbound

This paper cites Pipedream: gen- eralized pipeline parallelism for dnn training.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Pipedream: gen- eralized pipeline parallelism for dnn training

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.490548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3e7aea7c-03f5-435c-a20b-bb02b85b1657 · outbound

This paper cites GPT-4 Technical Report.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills GPT-4 Technical Report

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:31:47.363642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5acd7e4e-86ab-4722-8564-226b18a2a283 · outbound

This paper cites Efficiently scaling transformer inference.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Efficiently scaling transformer inference

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.493754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation be8945db-5e77-470a-89e5-db6a777c31e8 · outbound

This paper cites Rabe and Charles Staats.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Rabe and Charles Staats

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.497115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 217f0a45-d75c-46a4-82a5-905704a3d4f9 · outbound

This paper cites Fast transformer decoding: One write- head is all you need.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Fast transformer decoding: One write- head is all you need

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.500267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 072d2831-7e23-465d-abb9-25b1180f7b16 · outbound

This paper cites Fu, Zhiqiang Xie, Beidi Chen, Clark Barrett, Joseph E.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Fu, Zhiqiang Xie, Beidi Chen, Clark Barrett, Joseph E

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.504655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a8d9d635-39ef-4241-8838-2d62a9677aad · outbound

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

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:31:47.377211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 30a76471-d0e8-45a1-871f-a6cae359a10e · outbound

This paper cites Retentive network: A successor to transformer for large language models.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Retentive network: A successor to transformer for large language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.509432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6d805c9c-26f5-4ccb-9f51-85326a5dead2 · outbound

This paper cites Chi, Tat- sunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Chi, Tat- sunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.512757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9f7c027a-6cd8-4c75-b390-5e21be4f88f1 · outbound

This paper cites Fast distributed inference serving for large language models.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Fast distributed inference serving for large language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.515978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 88eb4b57-e784-4861-8c1a-1ad18faf17fe · outbound

This paper cites Smoothquant: Accu- rate and efficient post-training quantization for large language models.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Smoothquant: Accu- rate and efficient post-training quantization for large language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.519160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4ea16e24-5c31-490d-9cd4-83eb87925b95 · outbound

This paper cites Orca: A distributed serving system for Transformer-Based generative mod- els.

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Orca: A distributed serving system for Transformer-Based generative mod- els

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:31:47.525359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation fe6461ac-5e7b-4f5d-bc39-59168f834719 · inbound

A Survey on Efficient Inference for Large Language Models cites this paper.

A Survey on Efficient Inference for Large Language Models SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 282

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4abe331b-dea7-429e-ba62-883728ee7af3 · inbound

HybridFlow: A Flexible and Efficient RLHF Framework cites this paper.

HybridFlow: A Flexible and Efficient RLHF Framework SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03427540-7973-4bf9-81b7-c76b81325c5a · inbound

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads cites this paper.

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T11:49:16.707196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 46754dae-cb19-485e-a3fa-b617fed68ded · inbound

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching cites this paper.

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T16:58:11.909937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 69c6f004-7f74-445a-aa37-fe42a90f72e9 · inbound

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints cites this paper.

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-22T19:45:03.952532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b6323c5-3711-4110-b424-4813dec83e4f · inbound

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference cites this paper.

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 99981bc5-d0a4-49de-a7c1-f551b1b376a8 · inbound

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators cites this paper.

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T02:00:39.372114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b847bca7-d887-4b86-a732-357b7bab6771 · inbound

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators cites this paper.

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-16T23:58:42.971189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 477b55fb-b7f4-4549-b48c-4db1c93ae349 · inbound

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems cites this paper.

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T12:15:06.813295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1fe7abec-fc54-4930-b95b-570e5b69389c · inbound

MineDraft: A Framework for Batch Parallel Speculative Decoding cites this paper.

MineDraft: A Framework for Batch Parallel Speculative Decoding SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T21:14:46.669096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fb2bc04-fe28-4b80-ac28-0de489d8a815 · inbound

MC-CPO: Mastery-Conditioned Constrained Policy Optimization for Pedagogically Safe Intelligent Tutoring Systems cites this paper.

MC-CPO: Mastery-Conditioned Constrained Policy Optimization for Pedagogically Safe Intelligent Tutoring Systems SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T10:30:21.369025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2095a72b-29ea-4b2a-9214-62c9df2099f3 · inbound

Valve: Production Online-Offline Inference Colocation with Jointly-Bounded Preemption Latency and Rate cites this paper.

Valve: Production Online-Offline Inference Colocation with Jointly-Bounded Preemption Latency and Rate SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1d19e4f0-00d1-4c70-adb2-c60c3e58c9b7 · inbound

Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees cites this paper.

Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5b5e4f32-6891-40e8-b599-9ed2b0bdcda3 · inbound

Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs cites this paper.

Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f552e6cc-291e-4fd6-b5a1-1cb3ebfb1402 · inbound

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding cites this paper.

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c7d2a04-1531-4ce8-bb39-8401e855bb25 · inbound

AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving cites this paper.

AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57459ce9-f5b2-40e0-8e67-b098b2e4c155 · inbound

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving cites this paper.

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 45f9f4c5-2df1-4438-9432-efc6ee4104f3 · inbound

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems cites this paper.

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2be23e24-8a6f-4e5d-9e05-c97a6778dd31 · inbound

EdgeFM: Efficient Edge Inference for Vision-Language Models cites this paper.

EdgeFM: Efficient Edge Inference for Vision-Language Models SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 12f4c3e5-f983-4d7e-a3d1-950e5b34a66a · inbound

EdgeFM: Efficient Edge Inference for Vision-Language Models cites this paper.

EdgeFM: Efficient Edge Inference for Vision-Language Models SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-01T08:55:34.732042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1f32c318-668d-4544-9bcd-c918306c2685 · inbound

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving cites this paper.

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 477ce940-9db6-4f33-af43-ec239089882b · inbound

PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers cites this paper.

PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1963e390-410a-4633-9172-f1778c1d7c3f · inbound

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference cites this paper.

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a5c63d26-c383-43fd-a980-76a81b75c7af · inbound

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference cites this paper.

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-01T00:35:10.235272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e0f9de6d-25c9-47db-8e77-3506007e33a8 · inbound

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving cites this paper.

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9f64a633-45d3-4dc7-92ba-1a9c74883330 · inbound

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving cites this paper.

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-19T17:47:42.025621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 294494ee-41a1-4a85-aeab-d53556d90933 · inbound

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference cites this paper.

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1672a77c-5603-4e69-9190-7b6a1395e35c · inbound

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference cites this paper.

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2168dfa0-e6e7-4c2b-beb1-4b679bfe853d · inbound

Training-Inference Consistent Segmented Execution for Long-Context LLMs cites this paper.

Training-Inference Consistent Segmented Execution for Long-Context LLMs SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 21e964eb-0864-46e1-b933-fce79a301279 · inbound

The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures cites this paper.

The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:31:47.535686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fb7488f5-483e-447d-a260-5b81a734ce55 · inbound

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection cites this paper.

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-19T21:22:47.960862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 760b1ed1-c8fb-41bc-8920-71fee3715f0e · inbound

Beyond Scaling: Agents Are Heading to the Edge cites this paper.

Beyond Scaling: Agents Are Heading to the Edge SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:53:14.935042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3aa6fc2c-e0f9-40a7-ba07-69dfe47f7249 · inbound

KVBuffer: IO-aware Serving for Linear Attention cites this paper.

KVBuffer: IO-aware Serving for Linear Attention SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T12:03:15.260675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78ccea88-cc51-4bc3-adca-e216a2848772 · inbound

Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption cites this paper.

Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:58:04.862805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2dd0a23f-066c-4141-9f14-2f9b8061721e · inbound

Understanding Inference Scaling for LLMs: Bottlenecks, Trade-offs, and Performance Principles cites this paper.

Understanding Inference Scaling for LLMs: Bottlenecks, Trade-offs, and Performance Principles SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T02:12:58.271581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d1eb6d41-9712-4c4a-bf3a-cb16e797ba18 · inbound

Frontier: Towards Comprehensive and Accurate LLM Inference Simulation cites this paper.

Frontier: Towards Comprehensive and Accurate LLM Inference Simulation SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-21T03:49:31.093477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f312682-f682-4d2d-8c83-9582019b93c4 · inbound

AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System cites this paper.

AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-25T03:15:17.303901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 25b7cead-120f-477d-99f3-08adeda338f8 · inbound

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture cites this paper.

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:44:45.607766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eed0d6e2-6f1f-4ac5-abb2-b116cc224555 · inbound

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving cites this paper.

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-29T14:13:29.987690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 748ada5c-771b-459a-a0ab-0341f53d841b · inbound

DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference cites this paper.

DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:06:40.708633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e6fd6099-1cf8-45f5-820c-ab3e9b1da9c1 · inbound

Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference cites this paper.

Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-02T15:27:06.046624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 093eaa09-3de9-45f5-b0a4-dcbc4333307b · inbound

Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving cites this paper.

Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:06:56.124678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b62544c9-918c-4d02-a3a5-d65f9598d3cc · inbound

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design cites this paper.

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-03T07:27:44.463957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5a4533d2-5f58-4f84-aa5c-5b6e1c69650a · inbound

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill cites this paper.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.785034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 001e5b19-1864-4616-932c-50058cf2494e · inbound

LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs cites this paper.

LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-04T11:59:50.605397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 55d8ed2b-9a86-44fa-8e1e-ed2a07997247 · inbound

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs cites this paper.

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-02T21:07:23.425299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 91a132f0-dacf-4838-a14c-0b6a4a24dd4d · inbound

KernelSight-LM: A Kernel-Level LLM Inference Simulator cites this paper.

KernelSight-LM: A Kernel-Level LLM Inference Simulator SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T16:15:49.765804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67be4816-2fe7-469e-b273-0698ee5d3ed6 · inbound

KernelSight-LM: A Kernel-Level LLM Inference Simulator cites this paper.

KernelSight-LM: A Kernel-Level LLM Inference Simulator SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T23:19:02.751862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db4971cb-75b1-46cc-a5bc-9efe313ef085 · inbound

Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting cites this paper.

Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T17:31:15.972423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c91eeed-246f-4938-89dd-1552cefc34ba · inbound

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving cites this paper.

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T09:50:23.266920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673c8a16-7e9e-488c-813f-c4e0314ff1de · inbound

CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems cites this paper.

CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-10T16:37:23.050625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4ad8f6e-ec23-4eec-be11-31e37ec220d3 · inbound

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving cites this paper.

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T05:43:12.690359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfd6711a-345d-4153-b0ce-deb89e82792a · inbound

[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows cites this paper.

[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T07:51:15.549754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce8cbfb-3ea3-4862-a784-c002cdd0a97c · inbound

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models cites this paper.

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T21:32:01.677558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25433c1c-42f0-4738-9c5a-b4d897fd6b82 · inbound

A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing cites this paper.

A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-01T21:12:12.115153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986a2d1d-7550-43df-a407-ef37ae9c12e2 · inbound

DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs cites this paper.

DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T01:35:53.234326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83278f4-402a-4a2b-864e-341bc3b30f79 · inbound

Request-Level Energy Attribution for Batched LLM Serving cites this paper.

Request-Level Energy Attribution for Batched LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T01:44:54.104824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab8ae17b-813b-4f18-8c37-91a3224871ba · inbound

Action Chunk Scheduling for Batched Robot Policy Serving cites this paper.

Action Chunk Scheduling for Batched Robot Policy Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T00:44:24.913037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f6ae754-fee4-4a2b-a942-2cc2210b866c · inbound

Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling cites this paper.

Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T18:49:21.474198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33809743-9fe6-4fe0-afd9-442265d89329 · inbound

Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling cites this paper.

Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T10:54:00.298222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.