Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs | Paper Citation Record

Observation e81fbd40-63ff-4fc2-bd55-05114131724b · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 1

Resolution: parse uncertain; no resolver link, observed 2026-08-01T03:40:10.999156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da32b21-7b4a-4b7e-b44f-f20dc4ec28b5 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.005260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5039eec-7bfa-4d8e-85b5-96275f47ad23 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.010282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee08d559-9968-4f12-9b7c-842efcc8f3e2 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.016717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75dcedb9-39d9-49cb-8803-3983dd7e0a82 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.021558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acf32578-7480-4dd9-8ee9-a728a93cabdc · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.026430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398ec4d2-4f66-46a8-8a2b-aebc9527be8d · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 7

Resolution: parse uncertain; no resolver link, observed 2026-08-01T03:40:11.031727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6d493f9-cf75-428d-9f6b-79d4780f6d6c · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.035939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91212a2-8ee2-4d32-b5d3-de5ef048aaf6 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.040074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faf139c7-f5ae-4003-a1d8-05b1a98d601e · outbound

This paper cites Scissionlite: Accelerating distributed deep learning with lightweight data compression for iiot.IEEE Transac- tions on Industrial Informatics, 20(10):11950–11960, 2024.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Scissionlite: Accelerating distributed deep learning with lightweight data compression for iiot.IEEE Transac- tions on Industrial Informatics, 20(10):11950–11960, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.044193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfd4fa3d-553e-4145-a395-0831c5726fd3 · outbound

This paper cites Tooth: Toward optimal balance of video {QoE} and redundancy cost by {Fine- Grained}{FEC} in cloud gaming streaming.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Tooth: Toward optimal balance of video {QoE} and redundancy cost by {Fine- Grained}{FEC} in cloud gaming streaming

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.048531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a98f0dba-9b93-43cf-930d-3a588ffe6c00 · outbound

This paper cites Crux: Gpu-efficient communication scheduling for deep learning training.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Crux: Gpu-efficient communication scheduling for deep learning training

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.053431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aba9b77-b011-46a8-995d-5a2d2eb23de6 · outbound

This paper cites Eva: Cost- efficient cloud-based cluster scheduling.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Eva: Cost- efficient cloud-based cluster scheduling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.057720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af2baa5-b736-4b88-9b16-8515905d1d06 · outbound

This paper cites Kernel oper- ations on the gpu, with autodiff, without memory over- flows.Journal of Machine Learning Research, 22(74):1– 6, 2021.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Kernel oper- ations on the gpu, with autodiff, without memory over- flows.Journal of Machine Learning Research, 22(74):1– 6, 2021

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.061940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bbd9110-e6f2-46af-85ee-526807ff3686 · outbound

This paper cites Remote procedure call as a managed system service.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Remote procedure call as a managed system service

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.066423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 591726b1-51c1-47dc-b966-fdb425e9b7e1 · outbound

This paper cites Multiplexing dynamic deep learn- ing workloads with slo-awareness in gpu clusters.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Multiplexing dynamic deep learn- ing workloads with slo-awareness in gpu clusters

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.070517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45221d94-c5ea-4cb3-a447-c93037871049 · outbound

This paper cites {GRACE}:{Loss- Resilient}{Real-Time} video through neural codecs.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs {GRACE}:{Loss- Resilient}{Real-Time} video through neural codecs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.074609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7379fdeb-82e1-4252-8bb5-d5414e62298a · outbound

This paper cites Flashattention: Fast and memory- efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344– 16359, 2022.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Flashattention: Fast and memory- efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344– 16359, 2022

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.078564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4812f51-687c-4fc5-a585-03122aa6c47f · outbound

This paper cites Oneadapt: Fast adapta- tion for deep learning applications via backpropagation.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Oneadapt: Fast adapta- tion for deep learning applications via backpropagation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.083135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85a1258d-f65f-47ea-86ae-05737e63e0c4 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.087432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b7fc549-6faf-42cb-82e9-bc59ca50a6b4 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.091621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 379c6fbb-fec8-47e1-9d20-3021728b2615 · outbound

This paper cites Dgsf: Disaggregated gpus for serverless functions.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Dgsf: Disaggregated gpus for serverless functions

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.095749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 818656c9-a51e-4238-b955-4067ca201da4 · outbound

This paper cites Rdma over ethernet for distributed training at meta scale.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Rdma over ethernet for distributed training at meta scale

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.099856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d63b93d0-c65c-4979-947e-2eec9e855e89 · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.104095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee927be3-9751-4415-8937-0d7a837b8199 · outbound

This paper cites A gpgpu transparent virtualization component for high performance computing clouds.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A gpgpu transparent virtualization component for high performance computing clouds

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.108698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9ae254-bd5c-408d-9972-c3ec21c2066f · outbound

This paper cites Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.113329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e82ee4d-322c-478b-b98b-eddd16370dcd · outbound

This paper cites Kace: Kernel-aware colocation for effi- cient gpu spatial sharing.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Kace: Kernel-aware colocation for effi- cient gpu spatial sharing

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.120130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ca0d1e-f0ff-4e5f-a691-c506cc9959ad · outbound

This paper cites Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.125670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 834d32cb-73f6-4e79-96b7-042367f4f229 · outbound

This paper cites Multi-agent collaborative infer- ence via dnn decoupling: Intermediate feature compres- sion and edge learning.IEEE Transactions on Mobile Computing, 22(10):6041–6055, 2023.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Multi-agent collaborative infer- ence via dnn decoupling: Intermediate feature compres- sion and edge learning.IEEE Transactions on Mobile Computing, 22(10):6041–6055, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.130167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4fff8d-2f02-44bf-a2e0-5806d25bd8c6 · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.134612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6af4123f-65db-4204-9fe1-e3ee783c1dfa · outbound

This paper cites In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 87–101, 2023.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 87–101, 2023

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.138890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 895f8f53-7860-40f3-8e5f-32e8a2ff6f53 · outbound

This paper cites Charlie Hu, Xiaojun Lin, and Nan Deng.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Charlie Hu, Xiaojun Lin, and Nan Deng

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.143422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a12eb9f5-097c-4c74-ade9-57c9a012db8c · outbound

This paper cites A house united within itself: Slo-awareness for on-premises containerized ml inference clusters via faro.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A house united within itself: Slo-awareness for on-premises containerized ml inference clusters via faro

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.147743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 817605af-c388-4aec-bca1-2b9a568f9d27 · outbound

This paper cites Mor- ley Mao.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Mor- ley Mao

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.152064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d512668-de1e-402f-84e4-697d9c7ef85a · outbound

This paper cites Deepum: Tensor migration and prefetching in unified memory.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Deepum: Tensor migration and prefetching in unified memory

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.156399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ab778c-3b3f-4b23-b486-80fd42e4dd23 · outbound

This paper cites A neural-network- based realization of in-network computation for the in- ternet of things.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A neural-network- based realization of in-network computation for the in- ternet of things

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.161088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee45b07-34d1-42ca-b61d-e5cee2fea889 · outbound

This paper cites {SuperServe}:{Fine-Grained} inference serving for unpredictable workloads.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs {SuperServe}:{Fine-Grained} inference serving for unpredictable workloads

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.165512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54e34d1c-f630-4ea1-b661-51f6b00f7317 · outbound

This paper cites A survey on in-network computing: Programmable data plane and technology specific applications.IEEE Communications Surveys & Tutorials, 25(1):701–761, 2023.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A survey on in-network computing: Programmable data plane and technology specific applications.IEEE Communications Surveys & Tutorials, 25(1):701–761, 2023

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.169742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d438c829-33e9-49ed-9b5d-8fc735a80211 · outbound

This paper cites Navigator: Dynamic multi-kernel scheduling to improve gpu per- formance.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Navigator: Dynamic multi-kernel scheduling to improve gpu per- formance

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.173949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57aef14b-de47-4fa5-a3d9-552485dd5783 · outbound

This paper cites Efficient memory manage- ment for large language model serving with pagedatten- tion.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Efficient memory manage- ment for large language model serving with pagedatten- tion

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.178278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2784287b-4418-4329-bb95-87bea9ede7f6 · outbound

This paper cites Forecasting gpu performance for deep learning train- ing and inference.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Forecasting gpu performance for deep learning train- ing and inference

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.182444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93854fcd-8bc9-495f-8ba3-0e35228838d0 · outbound

This paper cites A survey on large language model acceleration based on kv cache management, 2025.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A survey on large language model acceleration based on kv cache management, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.186651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f34cb6-8c73-46c1-bac8-e7ddd46290ff · outbound

This paper cites THC: Accelerating distributed deep learning using ten- sor homomorphic compression.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs THC: Accelerating distributed deep learning using ten- sor homomorphic compression

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.190669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8832f8da-a903-4fa7-a36e-7e876239de19 · outbound

This paper cites Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.195265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f757e3e-db2e-4b27-86fc-7c7bf30891d0 · outbound

This paper cites Incbricks: To- ward in-network computation with an in-network cache.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Incbricks: To- ward in-network computation with an in-network cache

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.199805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc3512f-8635-4f4a-a61d-ab588b7d3118 · outbound

This paper cites Cachegen: Kv cache compression and streaming for fast large lan- guage model serving.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Cachegen: Kv cache compression and streaming for fast large lan- guage model serving

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.204037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a2a691-484f-422e-ad78-ae137fa5c5cf · outbound

This paper cites A convnet for the 2020s.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A convnet for the 2020s

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.209596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d225d4c4-314e-4207-a6cf-e764f6337ada · outbound

This paper cites A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.216782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5147f1f6-46fc-4e50-8ab4-02134dfaec9b · outbound

This paper cites A survey of storage systems in the rdma era.IEEE Transac- tions on Parallel and Distributed Systems, 33(12):4395– 4409, 2022.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs A survey of storage systems in the rdma era.IEEE Transac- tions on Parallel and Distributed Systems, 33(12):4395– 4409, 2022

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.228099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 803fc393-b9d1-4a27-9bda-af2fae79b699 · outbound

This paper cites Skyserve: Serving ai mod- els across regions and clouds with spot instances.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Skyserve: Serving ai mod- els across regions and clouds with spot instances

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.240104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f7e2269-9f65-4a92-9f83-c07e307cbf42 · outbound

This paper cites Efficient scheduling policies for Microsecond-Scale tasks.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Efficient scheduling policies for Microsecond-Scale tasks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.252541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bf9d1f6-3277-4920-99de-e1685840341c · outbound

This paper cites To- ward performance-portable petsc for gpu-based exascale systems.Parallel Computing, 108:102831, 2021.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs To- ward performance-portable petsc for gpu-based exascale systems.Parallel Computing, 108:102831, 2021

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.266736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5220bb3a-f75b-48e1-ad6c-dcef1b447bc0 · outbound

This paper cites Porting warpx to gpu- accelerated platforms.Parallel Computing, 108:102833, 2021.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Porting warpx to gpu- accelerated platforms.Parallel Computing, 108:102833, 2021

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.285770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9cc23b-1df0-4c96-a5f0-166389d8f973 · outbound

This paper cites Jellyfish: Timely inference serving for dynamic edge networks.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Jellyfish: Timely inference serving for dynamic edge networks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.314644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf2f227-ab26-4dc9-9b0a-8a3d888cce04 · outbound

This paper cites Bringing umap closer to the speed of light with gpu acceleration.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Bringing umap closer to the speed of light with gpu acceleration

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.330029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e333a6ea-f011-4074-9c60-244140e14361 · outbound

This paper cites Nvidia nvswitch: The world’s highest- bandwidth on-node switch.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Nvidia nvswitch: The world’s highest- bandwidth on-node switch

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.337088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97e016e-0e66-4ac1-a005-0ec3c96f368a · outbound

This paper cites Gemel: Model merging for memory-efficient,real-time video analytics at the edge.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Gemel: Model merging for memory-efficient,real-time video analytics at the edge

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.344509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9ad0f5-3866-4e5e-8ef5-184567811aed · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.352874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e56c7da-083f-4b4d-9639-22c3682c3071 · outbound

This paper cites {CASSINI}:{Network-Aware} job scheduling in machine learning clusters.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs {CASSINI}:{Network-Aware} job scheduling in machine learning clusters

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.364647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b84179bc-e235-4d4c-ba79-78842ad7de83 · outbound

This paper cites Sentinel: Efficient tensor migration and allocation on heterogeneous memory systems for deep learning.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Sentinel: Efficient tensor migration and allocation on heterogeneous memory systems for deep learning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.372960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2900bced-7c98-4149-8e37-75d00f579e1d · outbound

This paper cites Enabling large dynamic neural net- work training with learning-based memory manage- ment.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Enabling large dynamic neural net- work training with learning-based memory manage- ment

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.379969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 748e008d-6c97-475a-b8f2-1ed5e89acc24 · outbound

This paper cites {Cloud-LoRa}: Enabling cloud radio access {LoRa} networks using reinforce- ment learning based {Bandwidth-Adaptive} compres- sion.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs {Cloud-LoRa}: Enabling cloud radio access {LoRa} networks using reinforce- ment learning based {Bandwidth-Adaptive} compres- sion

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.387513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b275ef95-bf4f-448f-9b27-da8cd39c9bc1 · outbound

This paper cites Exploiting simultaneous communications to accelerate data parallel distributed deep learning.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Exploiting simultaneous communications to accelerate data parallel distributed deep learning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.394196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 693cf1f8-96ac-43b0-b349-607ef9f9dd10 · outbound

This paper cites Orion: Interference-aware, fine-grained gpu sharing for ml ap- plications.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Orion: Interference-aware, fine-grained gpu sharing for ml ap- plications

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.400877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e32dc8d-be47-41bc-89af-2f2e08ef8975 · outbound

This paper cites gremote: Cloud ren- dering on gpu resource pool based on api-forwarding.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs gremote: Cloud ren- dering on gpu resource pool based on api-forwarding

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.416566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 188d3cf4-d525-4a75-9005-8c8caff3d0ab · outbound

This paper cites Lammps-a flexible simu- lation tool for particle-based materials modeling at the atomic, meso, and continuum scales.Computer physics communications, 271:108171, 2022.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Lammps-a flexible simu- lation tool for particle-based materials modeling at the atomic, meso, and continuum scales.Computer physics communications, 271:108171, 2022

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.440322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9075125-c546-4c9d-8edd-367ac0d72b9c · outbound

This paper cites Plssvm—parallel least squares support vector machine.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Plssvm—parallel least squares support vector machine

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.468036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5771c190-475e-4cae-95be-a852315c3cea · outbound

This paper cites Aqua: Network-accelerated memory offloading for llms in scale-up gpu domains.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Aqua: Network-accelerated memory offloading for llms in scale-up gpu domains

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.522658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ecc8377-7758-414f-9506-64ac79e2ed9a · outbound

This paper cites Coflow scheduling for llm training.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Coflow scheduling for llm training

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.576555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 158cf9d6-e008-4c7c-a59e-73473353b2b2 · outbound

This paper cites Characterizing Network Requirements for GPU API Remoting in AI Applications.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Characterizing Network Requirements for GPU API Remoting in AI Applications

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.630913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7884337-5363-4d05-b8a1-1ae263e751ab · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.675274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b25a7077-5fa2-4b4e-b832-c3e0c4d9b323 · outbound

This paper cites Beware of fragmentation: Scheduling {GPU-Sharing} workloads with fragmentation gradient descent.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Beware of fragmentation: Scheduling {GPU-Sharing} workloads with fragmentation gradient descent

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.755151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9fd065-ddb7-48c9-a4c8-7b2ef3390bcb · outbound

This paper cites Transparent {GPU} sharing in container clouds for deep learning workloads.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Transparent {GPU} sharing in container clouds for deep learning workloads

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.798443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e46584d6-1c14-4058-bc99-72391d454c51 · outbound

This paper cites Yan, and Junchen Jiang.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Yan, and Junchen Jiang

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.872455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c59993-3ce9-4598-a883-0405c0d8b2a1 · outbound

This paper cites Efficient tensor offloading for large deep-learning model training based on compute express link.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Efficient tensor offloading for large deep-learning model training based on compute express link

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:11.914851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0699efe-20a1-4124-a9e0-7c8f547898d5 · outbound

This paper cites Infless: a native serverless system for low-latency, high- throughput inference.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Infless: a native serverless system for low-latency, high- throughput inference

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.019245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e87e1bfe-f4ef-4c12-85e7-b6ea4ff2bef8 · outbound

This paper cites Deep compressive offloading: Speeding up neural net- work inference by trading edge computation for network latency.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Deep compressive offloading: Speeding up neural net- work inference by trading edge computation for network latency

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.078779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9dce3a7-97b3-4d3a-8f78-165427374f2d · outbound

This paper cites Horus: granular in-network task sched- uler for cloud datacenters.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Horus: granular in-network task sched- uler for cloud datacenters

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.186797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0525d198-f573-46b9-bfc1-ec895eb25d05 · outbound

This paper cites Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.308277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32543cfe-c61d-4c10-80df-6a54ead58c8c · outbound

This paper cites an unresolved cited work.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Unresolved cited work

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.369125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435783a6-c85b-4a06-95aa-502e3d4c7815 · outbound

This paper cites Expel: Llm agents are ex- periential learners.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Expel: Llm agents are ex- periential learners

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.439101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ba649ac-fb75-41ad-98e5-0ec9e7e9ca01 · outbound

This paper cites Efficient {Direct-Connect} topologies for collective communications.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Efficient {Direct-Connect} topologies for collective communications

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.509184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da20ac6b-e61e-4283-b465-2ecc048e4ac1 · outbound

This paper cites Tally: Non-intrusive performance isolation for concur- rent deep learning workloads.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Tally: Non-intrusive performance isolation for concur- rent deep learning workloads

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.594996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ea237c-f11d-4484-a700-a0a96ebfd31c · outbound

This paper cites Sglang: Efficient execution of structured language model pro- grams.Advances in neural information processing sys- tems, 37:62557–62583, 2024.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Sglang: Efficient execution of structured language model pro- grams.Advances in neural information processing sys- tems, 37:62557–62583, 2024

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.665111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab65e9fa-816f-4f3a-afe8-2b559f56f520 · outbound

This paper cites Kernelet: High- throughput gpu kernel executions with dynamic slicing and scheduling.IEEE Transactions on Parallel and Distributed Systems, 25(6):1522–1532, 2014.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Kernelet: High- throughput gpu kernel executions with dynamic slicing and scheduling.IEEE Transactions on Parallel and Distributed Systems, 25(6):1522–1532, 2014

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-01T03:40:12.683698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbee7ac1-5724-4102-8cf5-d0e06cce693b · outbound

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

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs Megascale-infer: Efficient mixture-of-experts model serving with disag- gregated expert parallelism

Reference 86

Resolution: malformed identifier; no resolver link, observed 2026-08-01T03:40:12.723229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers