ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill | Paper Citation Record

Observation 4be7d489-df1a-4ba7-b089-ea4b2a5d56a9 · outbound

This paper cites https://www.mindspore.cn/tutorials/experts /en/r2.3.1/operation/op_custom_ascendc.htm l, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill https://www.mindspore.cn/tutorials/experts /en/r2.3.1/operation/op_custom_ascendc.htm l, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46952001-3ba0-4468-8b77-6914942ff88a · outbound

This paper cites https://www.hiascend.com/cann, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill https://www.hiascend.com/cann, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35ecc77b-37c4-4f03-a616-725d857c5d5b · outbound

This paper cites https://www.hiasce nd.com/document/detail/zh/canncommercial/8 3RC1/API/ascendcopapi/atlasascendc_api_07_ 0102.html, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill https://www.hiasce nd.com/document/detail/zh/canncommercial/8 3RC1/API/ascendcopapi/atlasascendc_api_07_ 0102.html, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b596b1b-d4c9-4107-bf5b-a26d3232bc64 · outbound

This paper cites https://www.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill https://www

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 2026-08-11T06:34:44.6726+00:00.

Observation 7583702a-b018-4649-b582-ea1fa8804ad2 · outbound

This paper cites Striped Attention: Faster Ring Attention for Causal Transformers.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Striped Attention: Faster Ring Attention for Causal Transformers

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.802503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 76cdb926-82c6-488c-8fd9-d9ef18c7b3f9 · outbound

This paper cites Characterizing cloud-native llm inference at bytedance and exposing optimization challenges and opportunities for future ai accelerators.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Characterizing cloud-native llm inference at bytedance and exposing optimization challenges and opportunities for future ai accelerators

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ece214-3270-4622-80a8-f4a374c28a19 · outbound

This paper cites Amali: An analytical model for accurately modeling llm inference on modern gpus.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Amali: An analytical model for accurately modeling llm inference on modern gpus

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d6f262-50ac-4bf9-8823-25dafbf881aa · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Generating Long Sequences with Sparse Transformers

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.829437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d8d69d94-1d59-4810-8994-04f8cff8dafe · outbound

This paper cites Lazy batching: An sla-aware batching system for cloud ma- chine learning inference.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Lazy batching: An sla-aware batching system for cloud ma- chine learning inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acf6493-f839-4647-ab64-2e53476e2ff9 · outbound

This paper cites Prediction is all moe needs: Expert load distribution goes from fluctuating to stabilizing, 2024.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Prediction is all moe needs: Expert load distribution goes from fluctuating to stabilizing, 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f72e47b-de4b-4814-af1f-b1db31a7ade4 · outbound

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

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T09:39:46.819780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cb4737a2-5bb0-45e9-b72a-4fad63616e2e · outbound

This paper cites Deepseek-v3 technical report, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Deepseek-v3 technical report, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 703825ae-cb2d-46d9-8535-07ccb01863ce · outbound

This paper cites Longnet: Scaling transformers to 1,000,000,000 tokens, 2023.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Longnet: Scaling transformers to 1,000,000,000 tokens, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2be5df-f02b-4fcb-84cb-790b57ddc27c · outbound

This paper cites GLaM: Efficient Scaling of Language Models with Mixture-of-Experts.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.809933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation edf51e26-9bc1-4bf6-b721-ba265cb41aeb · outbound

This paper cites Switch transformers: scaling to trillion parameter models with simple and efficient sparsity.J.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Switch transformers: scaling to trillion parameter models with simple and efficient sparsity.J

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bb45f1-1410-4d86-96ba-796e23276792 · outbound

This paper cites Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.812502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8fdd3057-98ec-426d-bf98-3a00b1799f2d · outbound

This paper cites TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.822145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cb28a707-1303-41c5-8403-1b2d4f7a93ed · outbound

This paper cites Past-future scheduler for llm serving under sla guar- antees.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Past-future scheduler for llm serving under sla guar- antees

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50cd2131-44bf-4af8-9404-d4bb2279ba9f · outbound

This paper cites FlashDecoding++: Faster Large Language Model Inference on GPUs.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill FlashDecoding++: Faster Large Language Model Inference on GPUs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.800083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 116ba9ea-3c2a-4e3b-8b0d-22aa9632bda0 · outbound

This paper cites MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.805074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4530887f-bca3-46b8-9a18-a835f7d32302 · outbound

This paper cites Deepserve: serverless large language model serving at scale.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Deepserve: serverless large language model serving at scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a5961b-40c0-4a6a-9690-de00f01a1bd8 · outbound

This paper cites Ad- vancing transformer architecture in long-context large language models: A comprehensive survey, 2024.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Ad- vancing transformer architecture in long-context large language models: A comprehensive survey, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ebf2254-cd6c-4997-a6d5-6e83ad6d8079 · outbound

This paper cites Transformers are rnns: Fast autoregressive transformers with linear attention.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Transformers are rnns: Fast autoregressive transformers with linear attention

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e972d62-124e-40de-a8b9-15103e96bfc5 · outbound

This paper cites Efficient memory man- agement for large language model serving with page- dattention.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Efficient memory man- agement for large language model serving with page- dattention

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 204977dd-947f-455d-8da1-0a766ba8ca82 · outbound

This paper cites Lightseq: : Sequence level parallelism for distributed training of long context transformers.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Lightseq: : Sequence level parallelism for distributed training of long context transformers

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02cb5f7-b5af-431a-a4ad-2b877e49476e · outbound

This paper cites Sequence Parallelism: Long Sequence Training from System Perspective.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Sequence Parallelism: Long Sequence Training from System Perspective

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.807624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 805686ed-6088-4442-a425-2d0dba339105 · outbound

This paper cites Ub-mesh: A hierarchically localized nd-fullmesh data center network architecture.IEEE Micro, 45(5):20–29, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Ub-mesh: A hierarchically localized nd-fullmesh data center network architecture.IEEE Micro, 45(5):20–29, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5178e071-885e-44f4-8fed-b50993fa7318 · outbound

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

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.797595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fa2864c0-9492-4731-a80c-3510d15ea2a7 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.787355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 20c1ff80-c833-4ead-a6a1-44a0ceb41827 · outbound

This paper cites Revealing the challenges of attention-ffn disaggregation for modern moe models and hardware systems.arXiv preprint arXiv:2602.09721, 2026.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Revealing the challenges of attention-ffn disaggregation for modern moe models and hardware systems.arXiv preprint arXiv:2602.09721, 2026

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.789810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0a329dab-8576-44f0-a9e7-cfadcdc99fbe · outbound

This paper cites Ring at- tention with blockwise transformers for near-infinite context.arXiv preprint arXiv:310.01889, 2023.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Ring at- tention with blockwise transformers for near-infinite context.arXiv preprint arXiv:310.01889, 2023

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f5b23ae-5053-4db6-8d7e-746955fdcb68 · outbound

This paper cites 2025.Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill 2025.Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.792483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 03c1d626-c481-4ac6-af08-f10b825c6b8d · outbound

This paper cites Moe-gps: Guid- lines for prediction strategy for dynamic expert duplica- tion in moe load balancing, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Moe-gps: Guid- lines for prediction strategy for dynamic expert duplica- tion in moe load balancing, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be696ba-5347-4158-9e67-559b2a5bff77 · outbound

This paper cites arXiv preprint arXiv:2503.07137 , year=.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill arXiv preprint arXiv:2503.07137 , year=

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T09:39:46.815037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 937fdc4d-98d1-4638-9c22-aa213a2491ed · outbound

This paper cites Mar- coni: Prefix caching for the era of hybrid llms.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Mar- coni: Prefix caching for the era of hybrid llms

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd4124e-755e-4399-9a2f-e562c7b2b729 · outbound

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

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Splitwise: Efficient generative llm inference using phase splitting

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ccbe570-388c-4600-8b89-ddc718145fc8 · outbound

This paper cites Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7cd991-c42b-453e-a73c-73526dfc7ad6 · outbound

This paper cites DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67934f4f-057e-4cfe-a62e-336c97447677 · outbound

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

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.827089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a43b99f4-1f84-4397-8ddb-1be63e5f172c · outbound

This paper cites Pangu pro moe: Mixture of grouped experts for efficient sparsity.arXiv preprint arXiv:505.21411, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Pangu pro moe: Mixture of grouped experts for efficient sparsity.arXiv preprint arXiv:505.21411, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc4d953c-4c6a-4efb-8ef7-09eec864a669 · outbound

This paper cites Kimi k2: Open agentic intelligence, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Kimi k2: Open agentic intelligence, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f27282-9de6-4598-8372-eb78e266ecd4 · outbound

This paper cites Thompson.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Thompson

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec2331c-7653-4b01-badd-d2332eab8495 · outbound

This paper cites Step-3 is large yet affordable: Model-system co-design for cost-effective decoding.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Step-3 is large yet affordable: Model-system co-design for cost-effective decoding

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.824708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e5d240f6-2937-4b2a-b7b8-7aa5bde81c8f · outbound

This paper cites Flexsp: Accelerating large language model training via flexible sequence parallelism.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Flexsp: Accelerating large language model training via flexible sequence parallelism

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff62471a-f5a9-4a92-8796-c1da20797600 · outbound

This paper cites {WLB-LLM}:{Workload-Balanced} 4d parallelism for large language model training.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill {WLB-LLM}:{Workload-Balanced} 4d parallelism for large language model training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbc5919-349b-4111-a6f4-99ccb0e1dbf7 · outbound

This paper cites Loongserve: Efficiently serving long-context large language models with elas- tic sequence parallelism.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Loongserve: Efficiently serving long-context large language models with elas- tic sequence parallelism

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49da9fe7-4f1a-49a3-be4e-3b78367201ee · outbound

This paper cites an unresolved cited work.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886bb5a6-d07d-4679-86a9-c50c313822ca · outbound

This paper cites Aegaeon: Effective gpu pooling for concurrent llm serving on the market.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Aegaeon: Effective gpu pooling for concurrent llm serving on the market

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c195a77-a5ef-4408-8357-4db76eeabaa6 · outbound

This paper cites ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-04T09:39:46.831727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bf273d27-d1ec-4a3c-9a26-d35ce2ddbcc3 · outbound

This paper cites Qwen3 technical report, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Qwen3 technical report, 2025

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57407930-470f-4da7-9341-e30756cfe0af · outbound

This paper cites Gonzalez, Clark Bar- rett, and Ying Sheng.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Gonzalez, Clark Bar- rett, and Ying Sheng

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb309625-d9bd-4e83-93d6-440d9cdf4534 · outbound

This paper cites Bucketserve: Bucket-based dynamic batching for smart and efficient llm inference serving.arXiv preprint arXiv:2507.17120, 2025.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Bucketserve: Bucket-based dynamic batching for smart and efficient llm inference serving.arXiv preprint arXiv:2507.17120, 2025

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.794999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f14d1e4d-49aa-47f7-85db-bf224efb8ad1 · outbound

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

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill {DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02da2d4b-9545-4a50-a8b0-d8587fa031ee · outbound

This paper cites Sampleattention: Near- lossless acceleration of long context llm inference with adaptive structured sparse attention.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Sampleattention: Near- lossless acceleration of long context llm inference with adaptive structured sparse attention

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6337a5f0-1d91-46be-a122-6f9dae8f542b · outbound

This paper cites Megascale-infer: Efficient mixture-of-experts model serving with disag- gregated expert parallelism.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Megascale-infer: Efficient mixture-of-experts model serving with disag- gregated expert parallelism

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-26T09:42:39.573568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a90714-7375-4a52-a134-3460c469c5e5 · outbound

This paper cites Serving Large Language Models on Huawei CloudMatrix384.

ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill Serving Large Language Models on Huawei CloudMatrix384

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:39:46.817497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers