Paper Citation Record · LEDGER

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference

As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2509.12993.

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

pith.paper-citation-record.v1
2509.12993 v3

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:35:35.426577Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 55e3c3f3-6dde-4b1f-bca1-8531a485b9af · outbound

This paper cites Language Models are Few-shot Learners,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Language Models are Few-shot Learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:29.783859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539b469b-dec8-4352-9cd3-702931516b18 · outbound

This paper cites Language Models are Unsupervised Multitask Learners,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Language Models are Unsupervised Multitask Learners,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:29.879160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f7029b4-940b-4fc8-9ed3-c07f0608e51d · outbound

This paper cites The Llama 3 Herd of Models.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference The Llama 3 Herd of Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:29.975362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9298850-d00c-4b54-ab18-14baab848e01 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference LLaMA: Open and Efficient Foundation Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.185854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c394fa82-02fb-4b67-b908-f2a6ee150e78 · outbound

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

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.323850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acf7df9-42e4-4e87-868d-846a56fa17ef · outbound

This paper cites Gorilla: Large Language Model Connected with Massive APIs,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Gorilla: Large Language Model Connected with Massive APIs,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.489832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96419213-16d0-49cb-8a47-00f387981659 · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Toolformer: Language Models Can Teach Themselves to Use Tools,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.636940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d50650-9c76-4c78-a20b-16dd986c319a · outbound

This paper cites FlashAt- tention: Fast and Memory-Efficient Exact Attention with IO- Awareness,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference FlashAt- tention: Fast and Memory-Efficient Exact Attention with IO- Awareness,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.762787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a324c9d2-589b-4e43-a641-95bbad295abb · outbound

This paper cites CodeGen: An Open Large Lan- guage Model for Code with Multi-Turn Program Synthesis,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference CodeGen: An Open Large Lan- guage Model for Code with Multi-Turn Program Synthesis,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:30.968441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7bea0c-9fbf-4911-9150-2fe4a0190830 · outbound

This paper cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.116711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df8fc92-8400-49a5-81f6-daa3467cd030 · outbound

This paper cites Au- toCodeRover: Autonomous Program Improvement,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Au- toCodeRover: Autonomous Program Improvement,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.255235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39e34a5a-4ed9-40ae-910d-d5b796719652 · outbound

This paper cites A 28nm 74.34 TFLOPS/W BF16 Heterogenous CIM-Based Accelerator Exploiting Denoising- Similarity for Diffusion Models,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference A 28nm 74.34 TFLOPS/W BF16 Heterogenous CIM-Based Accelerator Exploiting Denoising- Similarity for Diffusion Models,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.455325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1dc6e1f-9b81-4eda-92cb-ba60dea9fa9a · outbound

This paper cites SHMT: An SRAM and HBM Hybrid Computing-in-Memory Architec- ture With Optimized KV Cache for Multimodal Transformer,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference SHMT: An SRAM and HBM Hybrid Computing-in-Memory Architec- ture With Optimized KV Cache for Multimodal Transformer,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.558636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca90df65-b5a4-4841-a626-3537493b4995 · outbound

This paper cites DDC-PIM: Efficient Algorithm/Architecture Co-Design for Doubling Data Capac- ity of SRAM-based Processing-in-Memory,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference DDC-PIM: Efficient Algorithm/Architecture Co-Design for Doubling Data Capac- ity of SRAM-based Processing-in-Memory,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.722495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e720b3-298a-4319-9a34-fba5c0afd4a4 · outbound

This paper cites Towards Efficient SRAM- PIM Architecture Design by Exploiting Unstructured Bit-Level Sparsity,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Towards Efficient SRAM- PIM Architecture Design by Exploiting Unstructured Bit-Level Sparsity,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.813997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43e68926-0808-4416-b839-4ee73c70d1af · outbound

This paper cites CIMFlow: An Integrated Framework for Systematic Design and Evaluation of Digital CIM Architec- tures,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference CIMFlow: An Integrated Framework for Systematic Design and Evaluation of Digital CIM Architec- tures,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:31.902969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f23560e2-06fa-4315-a431-acea52597587 · outbound

This paper cites APIM: An Antiferromagnetic MRAM-Based Processing-In-Memory System for Efficient Bit-Level Opera- tions of Quantized Convolutional Neural Networks,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference APIM: An Antiferromagnetic MRAM-Based Processing-In-Memory System for Efficient Bit-Level Opera- tions of Quantized Convolutional Neural Networks,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.044140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f4aca76-0d1e-4c24-a842-284dd8172c52 · outbound

This paper cites TensorCIM: A 28nm 3.7 nJ/Gather and 8.3 TFLOPS/W FP32 Digital-CIM Tensor Processor for MCM-CIM-Based Beyond- NN Acceleration,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference TensorCIM: A 28nm 3.7 nJ/Gather and 8.3 TFLOPS/W FP32 Digital-CIM Tensor Processor for MCM-CIM-Based Beyond- NN Acceleration,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.153878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b0f795f-6e35-4962-8eb1-bad3115eee24 · outbound

This paper cites P 3ViT: A CIM-Based High-Utilization Architecture With Dynamic Pruning and Two-Way Ping-Pong Macro for Vision Transformer,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference P 3ViT: A CIM-Based High-Utilization Architecture With Dynamic Pruning and Two-Way Ping-Pong Macro for Vision Transformer,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.348498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d709bead-196e-4ad3-aca5-e18159443b7d · outbound

This paper cites PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.526309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8165e141-110a-40e2-980e-22fa7c866f33 · outbound

This paper cites SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.682558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e67c3a8-1591-4ab6-b2d0-5dd8efeeda6b · outbound

This paper cites An LPDDR-based CXL- PNM Platform for TCO-efficient Inference of Transformer- based Large Language Models,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference An LPDDR-based CXL- PNM Platform for TCO-efficient Inference of Transformer- based Large Language Models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.835843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1330221f-2ec0-4232-b915-5185dd7bb2ed · outbound

This paper cites Samsung PIM/PNM for Transfmer Based AI: Energy Efficiency on PIM/PNM Cluster,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Samsung PIM/PNM for Transfmer Based AI: Energy Efficiency on PIM/PNM Cluster,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:32.979354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4b6f34b-8a53-4b68-b480-dd6378257666 · outbound

This paper cites 3D-FPIM: An Extreme Energy-Efficient DNN Acceleration System Using 3D NAND Flash-Based In- Situ PIM Unit,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference 3D-FPIM: An Extreme Energy-Efficient DNN Acceleration System Using 3D NAND Flash-Based In- Situ PIM Unit,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.110041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5eb2248-28d9-45d4-a2fc-2bc76717baa8 · outbound

This paper cites S- FLASH: A NAND Flash-Based Deep Neural Network Acceler- ator Exploiting Bit-Level Sparsity,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference S- FLASH: A NAND Flash-Based Deep Neural Network Acceler- ator Exploiting Bit-Level Sparsity,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.312729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01172cf3-0b92-4b00-845e-a4dd9035b37b · outbound

This paper cites Attention is All You Need,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Attention is All You Need,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.506814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f9b910a-d679-40c1-8a37-5ee456650718 · outbound

This paper cites Deepspeed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Deepspeed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.624563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5111c646-bd43-44ea-92d3-22169b5cf35d · outbound

This paper cites DeepSpeed-Inference: Enabling Efficient Inference of Trans- former Models at Unprecedented Scale,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference DeepSpeed-Inference: Enabling Efficient Inference of Trans- former Models at Unprecedented Scale,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.759682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56688505-a8b2-4bcc-9b9b-e778f36b9c4e · outbound

This paper cites LLM Inference Unveiled: Survey and Roofline Model Insights.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.896184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db60f078-4690-430c-ab28-11ab198a8403 · outbound

This paper cites NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:33.993870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da08b751-8300-4cf5-8f0a-ff638df022e2 · outbound

This paper cites AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:34.198323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 424c1670-4686-4c76-b120-3ae9d2ba89f1 · outbound

This paper cites TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformer,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformer,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:34.395525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bad27cd6-f250-470f-a59d-2d355d1644ca · outbound

This paper cites IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:34.512136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021fe882-f553-4575-918e-a616a790ba24 · outbound

This paper cites Cambricon-LLM: A Chiplet- Based Hybrid Architecture for On-Device Lnference of 70B LLM,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Cambricon-LLM: A Chiplet- Based Hybrid Architecture for On-Device Lnference of 70B LLM,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:34.703201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8015d819-f95c-4fc1-8666-5b0c48c64001 · outbound

This paper cites Newton: A DRAM-maker’s Accelerator-in-Memory (AiM) Architecture for Machine Learn- ing,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference Newton: A DRAM-maker’s Accelerator-in-Memory (AiM) Architecture for Machine Learn- ing,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:34.875866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fa493c-0c0a-4a70-a32e-12a051198d4b · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference OPT: Open Pre-trained Transformer Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:35.054410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c2f1230-647b-4771-b556-c5290196b8c8 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:35.202801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10845d5-da08-4f4e-8865-d15d589abb9b · outbound

This paper cites DRAM- sim3: A Cycle-Accurate, Thermal-Capable DRAM Simulator,.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference DRAM- sim3: A Cycle-Accurate, Thermal-Capable DRAM Simulator,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:35.322780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fdb4bd-decf-4125-9733-0993a1020a45 · outbound

This paper cites High Bandwidth Memory DRAM (HBM3),.

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference High Bandwidth Memory DRAM (HBM3),

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T16:35:35.426577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.