PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving | Paper Citation Record

Observation 69d5d327-1c51-43aa-b2e7-55961ee8f14b · outbound

This paper cites Exploiting cxl-based memory for distributed deep learning,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Exploiting cxl-based memory for distributed deep learning,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.940781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec72d40d-779e-43d4-a574-f933cd47e04b · outbound

This paper cites Arm neoverse and NVIDIA NVLink fusion: AMBA CHI C2C interoperability for custom silicon,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Arm neoverse and NVIDIA NVLink fusion: AMBA CHI C2C interoperability for custom silicon,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.945642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91df20ec-a7c3-427b-87b3-7910274a157d · outbound

This paper cites Chameleon: Versatile and practical near-dram acceleration architecture for large memory systems,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Chameleon: Versatile and practical near-dram acceleration architecture for large memory systems,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.949840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6040c853-0872-4998-b5c9-bd66b582c377 · outbound

This paper cites Nvidia spent over $900 million on Enfabrica CEO, AI startup technology,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Nvidia spent over $900 million on Enfabrica CEO, AI startup technology,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.954261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7ae5f9-aab4-4f54-87cb-64fafbf91ef2 · outbound

This paper cites Punica: Multi-tenant lora serving,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Punica: Multi-tenant lora serving,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.595686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6d28489-d618-45aa-a872-469d226fd187 · outbound

This paper cites Compute express link (CXL) 3.1 specification,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Compute express link (CXL) 3.1 specification,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.579622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c2638423-f4ad-4744-b1d8-a09cb4b1bbe7 · outbound

This paper cites A Complete Survey on LLM-based AI Chatbots.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving A Complete Survey on LLM-based AI Chatbots

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.967888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be082b7b-97f9-4cf4-8b81-7d8ad4aaa47c · outbound

This paper cites FlashAttention-2: Faster attention with better parallelism and work partitioning,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving FlashAttention-2: Faster attention with better parallelism and work partitioning,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:32.972314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 549d4585-fc73-4410-8dab-b20d04845d6c · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Flashattention: Fast and memory-efficient exact attention with io-awareness,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.554629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ec7a543-b4d5-417b-81f7-bdb3f4a5ff72 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Qlora: Efficient finetuning of quantized llms,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.538778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0b17fcd5-ab90-4532-8d4c-70292885a26e · outbound

This paper cites The true processing in memory accelerator,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving The true processing in memory accelerator,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.522561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d22943f8-9e90-455f-8ecf-2fa41249627f · outbound

This paper cites EMFASYS: Elastic memory fabric system,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving EMFASYS: Elastic memory fabric system,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.505381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4018afc-1ed8-4e6d-a8c9-d3e82927ba00 · outbound

This paper cites NVIDIA Grace Hopper superchip architecture in-depth,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA Grace Hopper superchip architecture in-depth,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.490851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1fd79946-f20b-4e20-a11f-a7cd4a611884 · outbound

This paper cites Techniques for an efficient fabric attached memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Techniques for an efficient fabric attached memory,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.475522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de7a7073-e524-4e78-8b29-dec7ab493681 · outbound

This paper cites Techniques for an efficient fabric attached memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Techniques for an efficient fabric attached memory,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.458777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6a927501-7de5-428b-b7d4-d17a2429dc33 · outbound

This paper cites Low-overhead general-purpose near- data processing in CXL memory expanders,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Low-overhead general-purpose near- data processing in CXL memory expanders,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.443771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eed5a743-8521-4670-a697-eaa604297c51 · outbound

This paper cites Newton: A dram-maker’s accelerator-in- memory (aim) architecture for machine learning,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Newton: A dram-maker’s accelerator-in- memory (aim) architecture for machine learning,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.428864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 09ec8895-f7cb-45e9-bd3f-f7d10760ce01 · outbound

This paper cites Parameter-efficient transfer learning for nlp,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Parameter-efficient transfer learning for nlp,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.414123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 22742911-4acb-404a-a45d-193e5d4c90b1 · outbound

This paper cites Latency and bandwidth impact on GPU-systems,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Latency and bandwidth impact on GPU-systems,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.400026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e85fc5f0-5092-4beb-b585-cbae7e8308e7 · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving LoRA: Low-rank adaptation of large language models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.020108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3616a006-30da-4936-92bc-56eb63ef88a1 · outbound

This paper cites Achieving page-mapping ftl performance at block-mapping ftl cost by hiding address translation,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Achieving page-mapping ftl performance at block-mapping ftl cost by hiding address translation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.375521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a42e67e0-a5dd-4d2c-bf3a-ced8775ba74a · outbound

This paper cites Beacon: Scalable near-data-processing accelerators for genome analysis near memory pool with the cxl support,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Beacon: Scalable near-data-processing accelerators for genome analysis near memory pool with the cxl support,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.361324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf8c1e56-0e05-4c18-863e-8210e8fc30a9 · outbound

This paper cites Pifs-rec: Process- in-fabric-switch for large-scale recommendation system inferences,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Pifs-rec: Process- in-fabric-switch for large-scale recommendation system inferences,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.346166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 603106db-8e52-428a-ae24-61bfd7d88e38 · outbound

This paper cites CXL- ANNS:Software-Hardware collaborative memory disaggregation and computation for Billion-Scale approximate nearest neighbor search,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving CXL- ANNS:Software-Hardware collaborative memory disaggregation and computation for Billion-Scale approximate nearest neighbor search,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.331209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 87c81be1-a3bc-4fd6-9f5a-b51186bcc96a · outbound

This paper cites Demystifying a CXL type-2 device: A heterogeneous cooperative computing perspective,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Demystifying a CXL type-2 device: A heterogeneous cooperative computing perspective,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.316528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c4484558-365f-4596-83b0-dc321f67ef16 · outbound

This paper cites Near-memory processing in action: Accelerating personalized recommendation with AxDIMM,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Near-memory processing in action: Accelerating personalized recommendation with AxDIMM,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.301991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c081dc6-d69a-4784-9f6e-ca29ad58f597 · outbound

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

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Efficient memory management for large language model serving with pagedattention,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.288408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1265bc4-30ea-44d6-9eb3-14dd5778eb7d · outbound

This paper cites 25.4 a 20nm 6GB function-in-memory DRAM, based on HBM2 with a 1.2TFLOPS programmable computing unit using bank- level parallelism, for machine learning applications,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving 25.4 a 20nm 6GB function-in-memory DRAM, based on HBM2 with a 1.2TFLOPS programmable computing unit using bank- level parallelism, for machine learning applications,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.275160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 00d9074d-7b48-4743-83e8-d4504db83dbd · outbound

This paper cites TensorDIMM: A practical near-memory processing architecture for embeddings and tensor operations in deep learning,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving TensorDIMM: A practical near-memory processing architecture for embeddings and tensor operations in deep learning,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.260353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dbead095-a5e6-4a04-ac99-2ff2af513e90 · outbound

This paper cites Tensor casting: Co-designing algorithm- architecture for personalized recommendation training,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Tensor casting: Co-designing algorithm- architecture for personalized recommendation training,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.246975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eca4a8b5-00f1-4406-adcb-73789c572852 · outbound

This paper cites A 1ynm 1.25v 8gb, 16gb/s/pin gddr6-based accelerator- in-memory supporting 1tflops mac operation and various activation functions for deep-learning applications,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving A 1ynm 1.25v 8gb, 16gb/s/pin gddr6-based accelerator- in-memory supporting 1tflops mac operation and various activation functions for deep-learning applications,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.233422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6545275e-dcd4-4aa5-8c09-53d6b16eff9a · outbound

This paper cites Hardware architecture and software stack for PIM based on commercial DRAM technology: Industrial product,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Hardware architecture and software stack for PIM based on commercial DRAM technology: Industrial product,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.220462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e264a6ff-77c1-4c47-ab56-446455acbc6b · outbound

This paper cites Evaluating modern GPU interconnect: PCIe, NVLink, NV- SLI, NVSwitch and GPUDirect,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Evaluating modern GPU interconnect: PCIe, NVLink, NV- SLI, NVSwitch and GPUDirect,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.207615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e741aee0-a685-4f02-a73b-0f206e053179 · outbound

This paper cites Pond: CXL-based memory pooling systems for cloud platforms,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Pond: CXL-based memory pooling systems for cloud platforms,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.192748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 60d133cf-caeb-4cbc-9a60-cdddbcbacc21 · outbound

This paper cites CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.077193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef50a4e-316d-410a-856a-5dd7ebdebc21 · outbound

This paper cites Prefix-tuning: Optimizing continuous prompts for generation,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Prefix-tuning: Optimizing continuous prompts for generation,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.177710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d6d8838d-a5bb-424e-8d1b-fc5d791d6fa9 · outbound

This paper cites Disaggregated memory for expansion and sharing in blade servers,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Disaggregated memory for expansion and sharing in blade servers,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.163136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4ffefbb9-a924-487c-bd9a-e81df163b784 · outbound

This paper cites Enabling efficient large recommendation model training with near cxl memory processing,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Enabling efficient large recommendation model training with near cxl memory processing,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.146719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 347e8d3c-13c8-4fe8-9a7e-61b9f87035cb · outbound

This paper cites Make LLM inference affordable to everyone: Augmenting GPU memory with NDP-DIMM,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Make LLM inference affordable to everyone: Augmenting GPU memory with NDP-DIMM,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.131485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36dd16d6-4c5a-49ed-8a42-cb92310fcd23 · outbound

This paper cites The Llama 3 Herd of Models.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving The Llama 3 Herd of Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.096095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62cf7a44-592b-4eb0-b95b-2f84b28d772c · outbound

This paper cites LLaMAX: Scaling linguistic horizons of LLM by enhancing translation capabilities beyond 100 languages,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving LLaMAX: Scaling linguistic horizons of LLM by enhancing translation capabilities beyond 100 languages,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.115705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62eca269-efd8-45ca-a267-d14d13fef162 · outbound

This paper cites PEFT: State-of-the-art parameter-efficient fine-tuning methods,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving PEFT: State-of-the-art parameter-efficient fine-tuning methods,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.099912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b5618d45-e855-46a2-85eb-827313a7cf5d · outbound

This paper cites SiFive bakes NVIDIA’s NVLink fusion into its RISC-V CPU IP,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving SiFive bakes NVIDIA’s NVLink fusion into its RISC-V CPU IP,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.065572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 18542b4f-e8c7-4556-860c-3ea974fca217 · outbound

This paper cites Tpp: Transparent page placement for cxl-enabled tiered-memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Tpp: Transparent page placement for cxl-enabled tiered-memory,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:34.011878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d86235cc-866b-4886-b8b3-5a2f40470676 · outbound

This paper cites Marvell introduces breakthrough Structera CXL product line to address server memory bandwidth and capacity challenges in cloud data centers,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Marvell introduces breakthrough Structera CXL product line to address server memory bandwidth and capacity challenges in cloud data centers,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.979110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 615b1e46-b7d1-4296-81e4-5101c9121aa3 · outbound

This paper cites Specinfer: Accelerating large language model serv- ing with tree-based speculative inference and verification,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Specinfer: Accelerating large language model serv- ing with tree-based speculative inference and verification,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.958050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e5d50dd-e7e7-456a-b32a-08a12cd1e454 · outbound

This paper cites Micron launches memory expansion module portfolio to accelerate CXL 2.0 adoption,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Micron launches memory expansion module portfolio to accelerate CXL 2.0 adoption,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.941089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fee3e2c8-27f6-4956-bf35-a72e7b29a6c7 · outbound

This paper cites Nvidia licenses NVLink memory ports to CPU and accelerator makers,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Nvidia licenses NVLink memory ports to CPU and accelerator makers,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.925238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34036524-fbd9-43c8-8821-9108f983752e · outbound

This paper cites Using an llm to help with code understanding,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Using an llm to help with code understanding,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.130901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a18e6e79-f6ff-4149-a6c7-621212ebc081 · outbound

This paper cites Understanding pcie performance for end host networking,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Understanding pcie performance for end host networking,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.891676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb34a211-d656-430f-bb51-baa45980a68a · outbound

This paper cites NVIDIA A100 Tensor Core GPU Archi- tecture,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA A100 Tensor Core GPU Archi- tecture,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.873169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 023d15a2-8f36-47e2-91e6-0102727b2a7f · outbound

This paper cites NVIDIA H100 Tensor Core GPU Architecture,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA H100 Tensor Core GPU Architecture,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.856858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 65df5acb-b8f0-4302-8de1-f240d2fc1488 · outbound

This paper cites NVIDIA unveils NVLink fusion for industry to build semi-custom AI infrastructure with NVIDIA partner ecosystem,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA unveils NVLink fusion for industry to build semi-custom AI infrastructure with NVIDIA partner ecosystem,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.841798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f7b87e51-933d-474a-bbba-9fab2e07bccb · outbound

This paper cites Extended GPU memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Extended GPU memory,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.827502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 93ac9855-2b9e-4d34-ab4f-f830ec7374ad · outbound

This paper cites NVLink-C2C: Chip interconnect technology,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVLink-C2C: Chip interconnect technology,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.812443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ea828bc0-abbb-44b4-9b5c-7ce9a90578fa · outbound

This paper cites NVLink: The scale-up network for AI factories,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVLink: The scale-up network for AI factories,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.798540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37772516-2d86-4f4a-be92-45fe20ade695 · outbound

This paper cites GPT-4 Technical Report.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving GPT-4 Technical Report

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.164550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89914902-774f-440e-ba6a-81f29c951446 · outbound

This paper cites Attacc! unleashing the power of pim for batched transformer- based generative model inference,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Attacc! unleashing the power of pim for batched transformer- based generative model inference,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.783222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16ead26d-fcc7-4674-b0aa-c35531f3fcb3 · outbound

This paper cites Trim: Enhancing processor-memory interfaces with scalable tensor reduction in memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Trim: Enhancing processor-memory interfaces with scalable tensor reduction in memory,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.768997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 421507d8-8832-4f9f-b084-7326cc4b1248 · outbound

This paper cites An LPDDR-based CXL-PNM platform for TCO-efficient inference of transformer-based large language models,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving An LPDDR-based CXL-PNM platform for TCO-efficient inference of transformer-based large language models,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.754061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7b524d22-1bff-4130-a21e-a660c63023db · outbound

This paper cites System optimization of data analytics platforms using compute express link (CXL) memory,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving System optimization of data analytics platforms using compute express link (CXL) memory,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.738800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 714db274-4749-48b0-926c-472b1b40c875 · outbound

This paper cites Samsung CXL solutions: CMM-H (CXL memory module – hybrid),.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Samsung CXL solutions: CMM-H (CXL memory module – hybrid),

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.724966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7f7d6d72-7bf6-4290-9b39-d252786c12ac · outbound

This paper cites Flashattention-3: Fast and accurate attention with asynchrony and low- precision,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Flashattention-3: Fast and accurate attention with asynchrony and low- precision,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.669240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26fd3423-b93e-4e2c-8902-2e5e32978542 · outbound

This paper cites Pci express® 6.0 specification at 64.0 gt/s with pam- 4 signaling: a low latency, high bandwidth, high reliability and cost- effective interconnect,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Pci express® 6.0 specification at 64.0 gt/s with pam- 4 signaling: a low latency, high bandwidth, high reliability and cost- effective interconnect,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.649764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f287182-2079-498a-a837-c5cfdaa79027 · outbound

This paper cites S-LoRA: Serving thousands of concurrent LoRA adapters,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving S-LoRA: Serving thousands of concurrent LoRA adapters,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.631792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c2db919a-02dd-485c-bd2c-4c5b9a6963b8 · outbound

This paper cites Flexgen: High-throughput generative inference of large language models with a single gpu,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Flexgen: High-throughput generative inference of large language models with a single gpu,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.615867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e962fbe3-bb83-4e95-821d-d784465916ce · outbound

This paper cites NVIDIA announces NVLink fusion: Bringing NVLink to third-party CPUs and accelerators,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA announces NVLink fusion: Bringing NVLink to third-party CPUs and accelerators,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.600341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06ac0306-38c1-4bac-9d86-33e22411884e · outbound

This paper cites Demysti- fying CXL memory with genuine CXL-ready systems and devices,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Demysti- fying CXL memory with genuine CXL-ready systems and devices,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.585491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation be69a7b1-3993-4468-8b85-b2dfe10148ae · outbound

This paper cites NVIDIA’s NVLink fusion stays proprietary, third parties can only work around it,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NVIDIA’s NVLink fusion stays proprietary, third parties can only work around it,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.571469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bba8b162-dc34-4b8a-863a-daefb14c5461 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.222028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de0703f1-8098-405e-87f4-b4059b6dbeac · outbound

This paper cites Introducing UALink 200g 1.0 specification,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Introducing UALink 200g 1.0 specification,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.555910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 77e29f3c-d11b-40bd-b72d-bcd1d63c4241 · outbound

This paper cites RAG-based LLM chatbot using Llama-2,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving RAG-based LLM chatbot using Llama-2,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.540781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 575ba757-7920-4f94-a221-c16d6aadc94d · outbound

This paper cites Attention is all you need,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Attention is all you need,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.233661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23d86cb9-f84e-41ac-bba5-004e4e5e0757 · outbound

This paper cites CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.514676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3ba0a593-5564-47de-b4e4-7e5ccfd899c7 · outbound

This paper cites Towards memory disaggregation via NVLink C2C: Benchmarking CPU-requested GPU memory access,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Towards memory disaggregation via NVLink C2C: Benchmarking CPU-requested GPU memory access,

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.499655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1546ed30-3624-4b56-89b0-ee37b2cf26a3 · outbound

This paper cites dLoRA: Dynami- cally orchestrating requests and adapters for LoRALLM serving,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving dLoRA: Dynami- cally orchestrating requests and adapters for LoRALLM serving,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.484647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a8b3a48-e8bc-44d1-becf-abaf1122fe09 · outbound

This paper cites Overcoming the memory wall with CXL- EnabledSSDs,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Overcoming the memory wall with CXL- EnabledSSDs,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.470176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 960e80d9-f6f7-4127-a171-cea507e390c1 · outbound

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

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Orca: A distributed serving system for Transformer-Based generative models,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.455342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8093c004-5ed9-452e-95d6-a765fd4b8ccd · outbound

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

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving SGLang: Efficient execution of structured language model programs,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.265097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd4b648-11f9-4093-a2db-1c85884fbc89 · outbound

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

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving DistServe: Disaggregating prefill and decoding for goodput- optimized large language model serving,

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.432764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1d2fd4d4-375a-4ec2-ab5a-989143d79c13 · outbound

This paper cites Remap-SSD: Safely and efficiently exploiting SSD address remapping to eliminate duplicate writes,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Remap-SSD: Safely and efficiently exploiting SSD address remapping to eliminate duplicate writes,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.418903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1859044a-ba1b-4bd1-b1f5-24b53dd0e992 · outbound

This paper cites NeoMem: Hardware/software co- design for CXL-native memory tiering,.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving NeoMem: Hardware/software co- design for CXL-native memory tiering,

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.403267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 75041bd3-741f-4775-9240-522b8c324162 · outbound

This paper cites Available: https://semiconductor.samsung.com/news- events/tech-blog/samsung-cxl-solutions-cmm-h/.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Available: https://semiconductor.samsung.com/news- events/tech-blog/samsung-cxl-solutions-cmm-h/

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:20:33.694035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 456926f1-a6f7-4ff2-a75d-4ae099b1492b · outbound

This paper cites Performance Characterizations and Usage Guidelines of Samsung CXL Memory Module Hybrid Prototype.

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving Performance Characterizations and Usage Guidelines of Samsung CXL Memory Module Hybrid Prototype

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T12:20:33.261299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers