Paper Citation Record · LEDGER

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding

As of 23 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 2 inbound Pith citation observations for arXiv:2506.11309.

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

pith.paper-citation-record.v1
2506.11309 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:15:45.012578Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:45:04.545787Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T18:45:05.618170Z

Reference resolution

51 of 51 outbound references displayed

verified exact2
verified fuzzy15
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3fb5538b-276a-41a3-b1cb-10b4667fce22 · outbound

This paper cites Tam- ing Throughput-Latency tradeoff in LLM inference with Sarathi-Serve.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Tam- ing Throughput-Latency tradeoff in LLM inference with Sarathi-Serve

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.562565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8d7ff1db-4df9-4718-89e9-f354a6150ac2 · outbound

This paper cites PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.871917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4592b5d3-f84d-4c94-824e-057e5bf26bf0 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.875561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9963ce5-e8b9-4e6b-8d8b-754c5d1f4f90 · outbound

This paper cites Large Language Models vs. Search Engines: Evaluating User Preferences Across Varied Information Retrieval Scenarios.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Large Language Models vs. Search Engines: Evaluating User Preferences Across Varied Information Retrieval Scenarios

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.879263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c754f5f-5702-4004-a0aa-5fb1673780cf · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.882400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdd14e65-f8a2-4532-b295-7d5ed4d5594e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Evaluating Large Language Models Trained on Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.888884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96447f0a-0d6b-47a8-b1b3-81e18e68e95e · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.892665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6635c0-7cf7-4eaf-a680-5b53ed6b59d1 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.895818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a82ae83-f87f-4e58-95e9-f708bc578699 · outbound

This paper cites DAPPLE: A Pipelined Data Parallel Approach for Training Large Models.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding DAPPLE: A Pipelined Data Parallel Approach for Training Large Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:15:45.367229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 49df5af8-e974-4540-b019-993b34b03e69 · outbound

This paper cites LongCoder: A Long-Range Pre-trained Language Model for Code Completion.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding LongCoder: A Long-Range Pre-trained Language Model for Code Completion

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.902945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb237d4-b7dc-4d72-8cdf-2f00cd1d398e · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.905754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef14264-c6a6-49ae-9bcb-ad5d004cddff · outbound

This paper cites Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:15:45.338849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab8f421f-7074-471e-a655-4a27f89380e3 · outbound

This paper cites Le, Yonghui Wu, and Zhifeng Chen.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Le, Yonghui Wu, and Zhifeng Chen

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.546350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 87637fcd-8ea2-4e70-8d37-31eb934ce7ee · outbound

This paper cites Language Models for Code Completion: A Practical Evaluation.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Language Models for Code Completion: A Practical Evaluation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.916662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f4ee4b-5f47-4d96-9197-7ef6c6fd25af · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.537938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aceba6d5-f5de-4472-912c-3836a932dde2 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.922026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87745101-6bcf-4d75-8363-4a2416d0daea · outbound

This paper cites Fast inference from transformers via speculative de- coding, 2023.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Fast inference from transformers via speculative de- coding, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.529451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3e99ce16-7dd7-4564-bf61-74a784243bc8 · outbound

This paper cites EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.927085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1a7488-ce17-4678-a6ba-c130cc8374ba · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.929623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c5ef95b-fca0-489f-ba9f-d01467c1509d · outbound

This paper cites PEARL: Parallel Speculative Decoding with Adaptive Draft Length.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.932462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff29de01-5fa9-470f-b85a-f1ce27a5a5ab · outbound

This paper cites TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.934977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04da29a-e91d-4121-9b85-9c9c9a1bacee · outbound

This paper cites CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.937596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4e72ecd-1580-42b7-a2b4-9e8959a0f456 · outbound

This paper cites AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.940584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a796db2-febf-4c3c-9bad-4b3df007c4fe · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative infer- ence and verification.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Specinfer: Accelerating large language model serving with tree-based speculative infer- ence and verification

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.943253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27849d61-0697-409b-9c04-2c4260d8ae7d · outbound

This paper cites Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.945536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0ab6bb1-7e66-4b45-a031-01bd48dfa83d · outbound

This paper cites Nvidia/tensorrt-llm: A tensorrt toolbox for optimized large language model inference.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Nvidia/tensorrt-llm: A tensorrt toolbox for optimized large language model inference

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.520123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2e8f0325-e1b0-49e7-9a34-bdf2c8fd3340 · outbound

This paper cites GPT-4 Technical Report.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding GPT-4 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.950907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413a2d54-8dab-4c49-b80e-d2ca69d2e918 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Splitwise: Efficient generative LLM inference using phase splitting

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.953411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45eb26d6-6f58-4d29-a6dd-14bc43a42ea6 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.956041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaa4fb03-50e6-4477-8c55-81b5318b63b5 · outbound

This paper cites Tatsu-lab/stanford-alpaca: Code and documentation to train stanford’s alpaca mod- els, and generate the data.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Tatsu-lab/stanford-alpaca: Code and documentation to train stanford’s alpaca mod- els, and generate the data

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.510400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b772985c-390f-4f4f-8d2f-06ffb9e55c33 · outbound

This paper cites CUTLASS, January.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding CUTLASS, January

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.500994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a5f09fc7-f62e-4b0a-b8fb-43ac80d9e983 · outbound

This paper cites Llama: Open and efficient foundation language models, 2023.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Llama: Open and efficient foundation language models, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.484956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b4221c45-d13b-498c-9c04-b597e23fd764 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.969070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79725ce1-bde8-4b1a-b38b-9657020b78eb · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.971675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcd83ab8-57ba-4e93-983b-2eeb8c57a941 · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.974746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9686e40c-03cc-4790-8961-f2f059f63c0b · outbound

This paper cites When Search Engine Services meet Large Language Models: Visions and Challenges.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding When Search Engine Services meet Large Language Models: Visions and Challenges

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.977729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe5bd438-7080-4835-87e7-d1c32d86c99e · outbound

This paper cites Qwen2 Technical Report.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Qwen2 Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.980434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e37bbea3-b624-4247-badc-0985b0956d72 · outbound

This paper cites PALR: Personalization Aware LLMs for Recommendation.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding PALR: Personalization Aware LLMs for Recommendation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.983354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6c1c76-ca47-4f89-a99e-90a37ce29d59 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Orca: A distributed serving system for Transformer-Based generative models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.471867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e17bc3b8-1bfe-46e7-9b63-be6229c899cf · outbound

This paper cites Fltrnn: Faithful long-horizon taskplanningforroboticswithlargelanguagemodels.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Fltrnn: Faithful long-horizon taskplanningforroboticswithlargelanguagemodels

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.991410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5390ded-a5b2-4eb2-9f0b-14ca9aa49a33 · outbound

This paper cites Prepacking: A simple method for fast prefilling and increased throughput in large language models, 2024.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Prepacking: A simple method for fast prefilling and increased throughput in large language models, 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.454968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 64966e2b-fdec-46df-9dff-219b634fbae3 · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.996326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5448a914-ed7d-4f69-9198-e5bea3bd5bf5 · outbound

This paper cites Gonzalez, Clark Barrett, and Ying Sheng.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Gonzalez, Clark Barrett, and Ying Sheng

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.446325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 45bfc0d8-6903-4663-91a2-b67ab244d231 · outbound

This paper cites DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.438465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 78327a17-ce95-4d19-8262-07a9811bd1bb · outbound

This paper cites Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:45.012578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f94357-1a95-4a21-8b21-fc9328f7be3d · outbound

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

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding SGLang: Efficient Execution of Structured Language Model Programs

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:45.001651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7eda31-2e22-4c88-94dc-78f0a44fab71 · outbound

This paper cites ISBN 978-1-939133- 40-3.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding ISBN 978-1-939133- 40-3

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.430088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8b24c817-30aa-4d89-83b7-fb108d0329d0 · outbound

This paper cites GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:44.913577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf9a324-ef29-4afa-a642-0e47de74a6b9 · outbound

This paper cites ISBN 978-1-939133- 28-1.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding ISBN 978-1-939133- 28-1

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.463041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 82fe9fe4-a7e4-402b-8803-a3c012037936 · outbound

This paper cites an unresolved cited work.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:15:45.492822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1b9cf4b0-5cc1-448d-b5d8-fdd725b6a0b1 · outbound

This paper cites ISBN 978-1-939133- 40-3.

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding ISBN 978-1-939133- 40-3

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:15:45.554474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 73e76fe6-46b5-44f6-a9f2-eec8c7d42f7f · inbound

ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling cites this paper.

ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:45:05.693179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 44023fab-b54f-4e68-933e-80447626be8f · inbound

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting cites this paper.

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T10:09:31.872801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.