Paper Citation Record · LEDGER

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference

As of 9 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 2 inbound Pith citation observations for arXiv:2508.19373.

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

pith.paper-citation-record.v1
2508.19373 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:53:31.121991Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:16:13.946445Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T14:19:54.305666Z

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy15
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 78aa2a76-a5c6-4126-907b-2a602040a306 · outbound

This paper cites Efficient Large Scale Language Modeling with Mixtures of Experts.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Efficient Large Scale Language Modeling with Mixtures of Experts

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:28.504969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8df2bef5-66bd-425c-944c-7d07216a5636 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:28.577800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a84a559f-a641-4df7-897c-a4e92ed5c209 · outbound

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

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:28.650393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2840d992-add2-4378-bd70-3d352bdd3536 · outbound

This paper cites DeepSeek-V3 Technical Report.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference DeepSeek-V3 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:28.788647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de6209a7-9317-4477-ae13-1488bb143802 · outbound

This paper cites Scaling vision with sparse mixture of experts,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Scaling vision with sparse mixture of experts,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:35.471837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1fe8b34c-17fa-42fa-bd32-2838f16b6e75 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Efficient memory management for large language model serving with pagedattention,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:35.213876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 804a2c0c-1dc3-47dc-a9f9-82497e7d3e21 · outbound

This paper cites DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.009532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2267c1e9-1983-472e-a626-811df387e571 · outbound

This paper cites Moesys: A distributed and efficient mixture-of-experts training and inference system for internet services,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Moesys: A distributed and efficient mixture-of-experts training and inference system for internet services,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:34.893015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d9a93d69-9e96-4857-b601-668103d04040 · outbound

This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.246910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0891a351-fee2-4949-8b0e-eadd58e3fc64 · outbound

This paper cites ST-MoE: Designing Stable and Transferable Sparse Expert Models.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference ST-MoE: Designing Stable and Transferable Sparse Expert Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.303551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32bea133-c8ac-4fac-88ad-5fcaa90b9656 · outbound

This paper cites Mixtral of Experts.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Mixtral of Experts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.456526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d1fffb-a61a-40c8-a54d-fda1aebfd43b · outbound

This paper cites Qwen1.5-moe: Matching 7b model performance with 1/3 activated parameters.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Qwen1.5-moe: Matching 7b model performance with 1/3 activated parameters

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:34.649050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b4145053-23c4-4042-9b99-8e4fbb40d428 · outbound

This paper cites Qwen2 technical report,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Qwen2 technical report,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:34.383939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bebc2fe6-f70e-47f9-b054-42ebf961b062 · outbound

This paper cites A tensorrt toolbox for optimized large language model inference.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference A tensorrt toolbox for optimized large language model inference

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:34.150158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7defcc0e-ab5d-4898-bf95-3bc49fd3b840 · outbound

This paper cites Sglang: Efficient execution of structured language model programs,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Sglang: Efficient execution of structured language model programs,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:33.863906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8a2df785-e639-439d-b2dd-6cafd657326f · outbound

This paper cites Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.967927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf46c29f-504f-411e-800f-c48a25a3b836 · outbound

This paper cites Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:30.143109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10fe3b85-88c6-4681-9a38-de8394dae73e · outbound

This paper cites Deepspeed-moe: Advancing mixture- of-experts inference and training to power next-generation ai scale,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Deepspeed-moe: Advancing mixture- of-experts inference and training to power next-generation ai scale,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:33.554501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 80bbc26a-33c2-4fec-9cf4-ddeb9c3bd5f6 · outbound

This paper cites A hybrid tensor-expert-data parallelism approach to optimize mixture- of-experts training,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference A hybrid tensor-expert-data parallelism approach to optimize mixture- of-experts training,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:33.247641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d4006313-5169-4be0-93d9-b7a563c8e2de · outbound

This paper cites Deepep: an efficient expert-parallel communication library.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Deepep: an efficient expert-parallel communication library

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:32.922786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation abc71dfc-ed1b-48f9-8d2e-e53006875e2d · outbound

This paper cites Alpa: Automating inter-and {Intra- Operator} parallelism for distributed deep learning,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Alpa: Automating inter-and {Intra- Operator} parallelism for distributed deep learning,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:32.709061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c9593ac8-d628-4788-b72f-54a186ca65ff · outbound

This paper cites Tutel: Adaptive mixture-of-experts at scale,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Tutel: Adaptive mixture-of-experts at scale,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:32.422585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3184221e-1e66-418f-8983-9e307435cec1 · outbound

This paper cites Pcie gen-5 design challenges of high-speed servers,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Pcie gen-5 design challenges of high-speed servers,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:32.187333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1bc0417a-b19b-4dc5-a8fc-f6eb5be375ca · outbound

This paper cites Nvidia a100 gpu: Performance & innova- tion for gpu computing,.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Nvidia a100 gpu: Performance & innova- tion for gpu computing,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:31.855990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e15fa19d-f1e5-42fe-8275-28e067506fe9 · outbound

This paper cites Bitsandbytes: a lightweight python wrapper around cuda custom func- tions.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference Bitsandbytes: a lightweight python wrapper around cuda custom func- tions

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:53:31.652787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ddd5ed51-d969-4652-bf2e-66513c54a65a · outbound

This paper cites A White Paper on Neural Network Quantization.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference A White Paper on Neural Network Quantization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:31.121991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 605ca0d3-c892-4868-8dad-b1eab5e2fa33 · inbound

Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch cites this paper.

Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:19:54.307203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 658b5d45-7a36-4a0d-8404-f8307c332c67 · inbound

Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference cites this paper.

Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T19:16:13.946445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.