Paper Citation Record · LEDGER

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

As of 3 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2605.07985.

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

pith.paper-citation-record.v1
2605.07985 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T10:20:45.375375Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+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

44 of 44 outbound references displayed

verified exact18
verified fuzzy19
unresolved0
parse uncertain1
malformed identifier4
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f5328f67-d8a0-4e06-864c-6b3dfa09ab1f · outbound

This paper cites URLhttps://developer.nvidia.com/cupti.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation URLhttps://developer.nvidia.com/cupti

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.200462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a929d66d-0f32-474b-a411-6b97ecb62280 · outbound

This paper cites URL https://docs.pytorch.org/tutorials/ recipes/recipes/profiler_recipe.html.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation URL https://docs.pytorch.org/tutorials/ recipes/recipes/profiler_recipe.html

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.204791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0c203058-aa1f-4c39-83db-a888fd5c1316 · outbound

This paper cites Vidur: A Large-Scale Simulation Framework For LLM Inference.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Vidur: A Large-Scale Simulation Framework For LLM Inference

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.846209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 74d58261-838b-4fd0-808d-b7d5c2fa05f4 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.908790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3172fe24-8cd0-41fc-a150-7bc8a21bc2ac · outbound

This paper cites Revati: Transparent gpu-free time-warp emulation for llm serving.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Revati: Transparent gpu-free time-warp emulation for llm serving

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.885158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ce950114-2d3f-44af-9e51-84605f9f3e20 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.864756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 054f693d-0569-4103-9b37-eaec98632265 · outbound

This paper cites vllm v1 performance optimization.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation vllm v1 performance optimization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.191099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 009ae2dc-da17-41e9-a1a6-1da67c424bd6 · outbound

This paper cites Flowdroid: precise context, flow, field, object-sensitive and lifecycle-aware taint analysis for android apps.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Flowdroid: precise context, flow, field, object-sensitive and lifecycle-aware taint analysis for android apps

Reference 8

Resolution: malformed identifier; arxiv_id, observed 2026-05-22T10:21:23.902334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation dc7372b2-dfb7-4258-ab09-e0ae8bbe5f08 · outbound

This paper cites Peters, and Arman Cohan.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Peters, and Arman Cohan

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.195664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 759531f3-8c17-40a9-b079-d9c45eb24908 · outbound

This paper cites Longformer: The Long-Document Transformer.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Longformer: The Long-Document Transformer

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.859081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4fe38901-838a-4ce5-ad65-c01ac960eeee · outbound

This paper cites SLOs-Serve: Optimized Serving of Multi-SLO LLMs.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation SLOs-Serve: Optimized Serving of Multi-SLO LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.920717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 22b3bfe9-c3c8-4d82-b19f-a8621e3f6d3f · outbound

This paper cites Llmservingsim: A hw/sw co-simulation infrastructure for llm inference serving at scale.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Llmservingsim: A hw/sw co-simulation infrastructure for llm inference serving at scale

Reference 12

Resolution: malformed identifier; arxiv_id, observed 2026-05-22T10:21:23.964247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 60463572-b9f7-4e42-9a0d-0fddb59fd3d3 · outbound

This paper cites Llmservingsim2.0: A unified simulator for het- erogeneous hardware and serving techniques in llm infrastructure.IEEE Computer Architecture Letters, 24(2):361–364, July 2025.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Llmservingsim2.0: A unified simulator for het- erogeneous hardware and serving techniques in llm infrastructure.IEEE Computer Architecture Letters, 24(2):361–364, July 2025

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.148976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a7a66680-9994-4ab0-b226-e9e213cb857d · outbound

This paper cites Coherelabs/c4ai-command-r7b-12-2024.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Coherelabs/c4ai-command-r7b-12-2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.209651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation de0e2621-d09f-4f90-8c66-fa4f8c735269 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T10:21:23.870869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 74f33378-fdee-438e-9aa2-d1f67177a19e · outbound

This paper cites Adapting vidur to vllm and profiling cpu overhead.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Adapting vidur to vllm and profiling cpu overhead

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.213995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d0f0d187-be0d-4e01-8178-e466e244c53a · outbound

This paper cites Cox, Jaeyeon Jung, Patrick McDaniel, and Anmol N.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Cox, Jaeyeon Jung, Patrick McDaniel, and Anmol N

Reference 17

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T10:21:25.218224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 60ed9ba8-68f0-44c7-b38b-8beeeb135190 · outbound

This paper cites Frontier: Simulating the Next Generation of LLM Inference Systems.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Frontier: Simulating the Next Generation of LLM Inference Systems

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.877745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c6a3ee4c-8928-4d87-bf0a-d33c8bf58146 · outbound

This paper cites How to get the profile csv of vllm instead of tensorrt-llm? https://github.com/ casys-kaist/LLMServingSim/issues/10.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation How to get the profile csv of vllm instead of tensorrt-llm? https://github.com/ casys-kaist/LLMServingSim/issues/10

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.222822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cbd2f16b-0585-420d-92b4-13ca88adb0fd · outbound

This paper cites Perfetto trace viewer.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Perfetto trace viewer

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.260581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 59afc0ab-bdc2-4fc5-8d89-c6a908422a7f · outbound

This paper cites Questions about simulation fidelity under vllm version differences, profiling utiliza- tion, and throughput estimation.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Questions about simulation fidelity under vllm version differences, profiling utiliza- tion, and throughput estimation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.187052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b5e94dda-f203-4f76-82c9-bf1b7312c9b4 · outbound

This paper cites Mixtral of Experts.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Mixtral of Experts

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.840418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation da79cacd-db46-4382-b608-2f0a7c5d7d18 · outbound

This paper cites Rogers, Tor M.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Rogers, Tor M

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.137659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation aa6391b6-7c2a-41f8-b8a5-18debb4bd7c1 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Gonzalez, Hao Zhang, and Ion Stoica

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.168308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f6ef9946-1994-40d8-90ad-b6335be2eaa4 · outbound

This paper cites APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.893409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f4e5065c-2bac-4ad8-9201-4cc59a83294a · outbound

This paper cites meta-llama/llama-3.1-8b.https://huggingface.co/meta-llama/Llama-3.1-8B.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation meta-llama/llama-3.1-8b.https://huggingface.co/meta-llama/Llama-3.1-8B

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.177822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 774b07b9-a065-43ab-b5fa-a1576ea5ca40 · outbound

This paper cites Dynamic taint analysis for automatic detection, analysis, and signature generation of exploits on commodity software.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Dynamic taint analysis for automatic detection, analysis, and signature generation of exploits on commodity software

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.172849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 51342f58-94ba-492b-b4e9-78d093efed26 · outbound

This paper cites openchat_sharegpt4_dataset.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation openchat_sharegpt4_dataset

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.182570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3810615a-248e-44f5-9d7b-af8b433f42a8 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Pytorch: An imperative style, high-performance deep learning library

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.265028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 34cec221-9895-4ea2-93b7-9fb19a6ad154 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Splitwise: Efficient generative LLM inference using phase splitting

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.951734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0a374a57-3407-4c84-b848-d93fc40c6062 · outbound

This paper cites GitHub - pytorch/kineto: A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation GitHub - pytorch/kineto: A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.250511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cb5325ed-7aba-4b7e-b1e1-cacff01c5ecf · outbound

This paper cites The anatomy of a triton attention kernel.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation The anatomy of a triton attention kernel

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.957706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 12447c86-b130-4eeb-9c69-c8ff35a2932c · outbound

This paper cites Running problems with replica scheduler orca/sarathi.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Running problems with replica scheduler orca/sarathi

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.255340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 415acae4-fab2-44f2-a70c-3ee4b3f0b4ac · outbound

This paper cites Adding new model.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Adding new model

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.241485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 379edae6-da17-4c29-9bf4-80a2e541f916 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.933069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2fd53c4c-aa90-4ec1-91a5-8556d7a4a344 · outbound

This paper cites Trtion.https://triton-lang.org/main/index.html.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Trtion.https://triton-lang.org/main/index.html

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.245947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 96741a9e-a8f9-4b6f-ba03-56285caffc49 · outbound

This paper cites Attention Is All You Need.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Attention Is All You Need

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.914260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation afdd0979-a995-4960-854d-45b980151840 · outbound

This paper cites Optimization and tuning.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Optimization and tuning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:21:25.236958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation be340fb5-53e1-4131-a294-6e289c2d1de8 · outbound

This paper cites Qwen2.5-1M Technical Report.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Qwen2.5-1M Technical Report

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.926791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7d2b2aba-b195-40a6-b041-97eb21c9455a · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:21:23.939335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 28060f05-4488-40bc-9fcd-36cec22f71c6 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation SGLang: Efficient Execution of Structured Language Model Programs

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T10:21:23.945417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3d128a9a-6b6c-4f2b-90a8-65647c752500 · outbound

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

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.852947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1052ea2a-b780-4a90-be3a-6f1635976c59 · outbound

This paper cites an unresolved cited work.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Unresolved cited work

Reference 43

Resolution: parse uncertain; raw_fallback, observed 2026-05-22T10:21:25.227519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ef50f773-b9dd-448d-924a-697ffae34778 · outbound

This paper cites Sufficiency of a single trace.A natural concern is whether a single dummy-prompt trace can cover both prefill and decode call paths.

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Sufficiency of a single trace.A natural concern is whether a single dummy-prompt trace can cover both prefill and decode call paths

Reference 44

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T10:21:25.232247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

No inbound Pith citation observations are available.