Paper Citation Record · LEDGER

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers

As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.25655.

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

pith.paper-citation-record.v1
2605.25655 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T20:33:14.055182Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

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

measured 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

38 of 38 outbound references displayed

verified exact15
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6d2edf1c-7b5c-4f01-a649-3537258fff8e · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers LLaMA: Open and Efficient Foundation Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.248919Z

Source-reported events for the cited work

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

Observation 95e28b52-88d2-4668-90fd-4cf9793b9d6f · outbound

This paper cites Qwen Technical Report.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Qwen Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.251341Z

Source-reported events for the cited work

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

Observation 1b25a901-7741-4fb2-8349-057b0166afb2 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.239994Z

Source-reported events for the cited work

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

Observation b24729db-6e86-48c9-b3d3-1f65efdda61e · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Efficient memory management for large language model serving with pagedattention,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e28ca0df-cba0-4d5a-bac2-94ae370e5abf · outbound

This paper cites TensorRT-LLM,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers TensorRT-LLM,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 657778f7-9fef-4f4c-89ee-d74f0b859b80 · outbound

This paper cites Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a82dc052-3a63-447a-b7f9-a44ca9487c34 · outbound

This paper cites Large- scale parallelization and optimization of lattice qcd on tianhe new generation supercomputer,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Large- scale parallelization and optimization of lattice qcd on tianhe new generation supercomputer,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9a3747-e92f-4425-857a-33790a644fc7 · outbound

This paper cites Mt-3000: a heterogeneous multi-zone processor for hpc,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Mt-3000: a heterogeneous multi-zone processor for hpc,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa0119f3-4f5a-4d2c-b148-846aa8e24575 · outbound

This paper cites Performance analysis of cuda, openacc and openmp programming models on tesla v100 gpu,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Performance analysis of cuda, openacc and openmp programming models on tesla v100 gpu,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae047b4-1459-4805-b46b-f74eb8462b31 · outbound

This paper cites Mpi: a standard message passing interface,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Mpi: a standard message passing interface,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a6cd98-85fd-4ac9-8cfd-58928f2157a2 · outbound

This paper cites Attention is all you need,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Attention is all you need,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d4df453-538a-457d-ad6a-318341307ef8 · outbound

This paper cites BERT: A Review of Applications in Natural Language Processing and Understanding.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers BERT: A Review of Applications in Natural Language Processing and Understanding

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-29T20:33:58.246290Z

Source-reported events for the cited work

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

Observation 0c4244fa-f83a-492e-9ffd-eeb09a8c6d1a · outbound

This paper cites Language models are unsupervised multitask learners,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Language models are unsupervised multitask learners,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab7d1c02-3047-42c2-8ab1-b67ecc721b36 · outbound

This paper cites Language mod- els are few-shot learners,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Language mod- els are few-shot learners,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aa8fd6e-d620-4b6c-bb35-add9719f99f9 · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.243502Z

Source-reported events for the cited work

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

Observation 1dea15d5-e615-4a35-a884-d6ba80c9ff79 · outbound

This paper cites The Llama 3 Herd of Models.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers The Llama 3 Herd of Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.246240Z

Source-reported events for the cited work

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

Observation 21f14377-3571-4e4f-9ba5-b10509f94842 · outbound

This paper cites DeepSeek-V3 Technical Report.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers DeepSeek-V3 Technical Report

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.272198Z

Source-reported events for the cited work

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

Observation 8ebbd727-232e-4a78-bfff-41660976d5a1 · outbound

This paper cites Qwen2 Technical Report.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Qwen2 Technical Report

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.275350Z

Source-reported events for the cited work

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

Observation b1f198ea-f712-4f87-bab2-ab647243519b · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.264414Z

Source-reported events for the cited work

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

Observation ddbe6671-80a4-4826-a793-95ae20a5bb46 · outbound

This paper cites Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a76898-7317-486d-9e37-429289e25055 · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Sparsegpt: Massive language models can be accurately pruned in one-shot,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f327fb1e-5677-4a0f-910b-04398689bbb4 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Llm-pruner: On the structural pruning of large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3dc798f-e95f-4069-b52d-59445f591d66 · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers MiniLLM: On-Policy Distillation of Large Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.259894Z

Source-reported events for the cited work

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

Observation 9f542ca8-bdeb-465e-ba21-48a3f60379c6 · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Flashattention: Fast and memory-efficient exact attention with io-awareness,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 888d6e6f-091a-4a3a-85ba-1992102554e9 · outbound

This paper cites Longformer: The Long-Document Transformer.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Longformer: The Long-Document Transformer

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.266584Z

Source-reported events for the cited work

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

Observation 542292c2-31d1-45dd-bcbd-b8c389648252 · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Linformer: Self-Attention with Linear Complexity

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.269898Z

Source-reported events for the cited work

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

Observation d95be2c3-ca5a-46fc-acc9-0b2073717876 · outbound

This paper cites Reformer: The Efficient Transformer.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Reformer: The Efficient Transformer

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.272420Z

Source-reported events for the cited work

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

Observation 45e8b6c0-c945-460d-948b-a0152440e980 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.257118Z

Source-reported events for the cited work

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

Observation c3ca5121-d7de-485e-b279-63a70b105c69 · outbound

This paper cites Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3237c88-7dea-4707-bf75-c063fed24f3e · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Efficient Streaming Language Models with Attention Sinks

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-06-29T20:33:58.255008Z

Source-reported events for the cited work

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

Observation f1090996-0c2c-44cb-bd2f-5cf32274a2a9 · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Orca: A distributed serving system for{Transformer-Based}generative models,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 233a8c46-11e2-40e9-9cd8-bc11ec110e61 · outbound

This paper cites Text Generation Inference,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Text Generation Inference,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bad1ad4-8492-4b17-8cd0-4099a8cf1dc4 · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Flexgen: High-throughput generative inference of large language models with a single gpu,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5361c5e1-7e74-4f72-afda-c3f52ffbf880 · outbound

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

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers {DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889c0a49-7b04-4a19-8809-a10db6997573 · outbound

This paper cites Efficient processing of deep neural networks: A tutorial and survey,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Efficient processing of deep neural networks: A tutorial and survey,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 894cf718-d9e1-42dc-bc74-dea31e4d690d · outbound

This paper cites Roofline: an insightful visual performance model for multicore architectures,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Roofline: an insightful visual performance model for multicore architectures,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41e96e60-b30d-4773-abe3-6f9f0800e040 · outbound

This paper cites Optimizing general matrix multiplications on modern multi-core dsps,.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers Optimizing general matrix multiplications on modern multi-core dsps,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6629f8c6-9f15-4ee2-a633-2beda16cb7db · outbound

This paper cites He served as the chief scientist of China National High Technology Program on high perfor- mance computing for 20 years.

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers He served as the chief scientist of China National High Technology Program on high perfor- mance computing for 20 years

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-29T20:33:14.055182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.