Paper Citation Record · LEDGER

Hardware-Efficient Attention for Fast Decoding

As of 22 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 5 inbound Pith citation observations for arXiv:2505.21487.

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

pith.paper-citation-record.v1
2505.21487 v1

Coverage vector

measured 85 of 85 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:32:35.413009Z

measured 90 of 90 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:48:01.180107Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-11T01:57:51.329269Z

Reference resolution

85 of 85 outbound references displayed

verified exact2
verified fuzzy13
unresolved69
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 43121bc2-b3cf-48bd-b5ec-d989455c453e · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

Hardware-Efficient Attention for Fast Decoding SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.014918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41699e1c-1716-4d8f-90e2-d7bf64aa9f0f · outbound

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

Hardware-Efficient Attention for Fast Decoding GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.108759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8abc7c3-bda3-4139-8f81-e0cb39023140 · outbound

This paper cites DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

Hardware-Efficient Attention for Fast Decoding DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.198408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71edab39-71ef-451a-b4ee-82e3c796a122 · outbound

This paper cites How to scale your model.

Hardware-Efficient Attention for Fast Decoding How to scale your model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.314397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006a6026-b703-4b2a-9bb7-af46222eabbe · outbound

This paper cites Round and Round We Go! What makes Rotary Positional Encodings useful?.

Hardware-Efficient Attention for Fast Decoding Round and Round We Go! What makes Rotary Positional Encodings useful?

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.405631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0705c79f-e322-49e3-8af2-b710e8b0cbde · outbound

This paper cites Singe: Leveraging warp specialization for high performance on gpus.

Hardware-Efficient Attention for Fast Decoding Singe: Leveraging warp specialization for high performance on gpus

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.516253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c62b84a-73c0-4045-b3a2-e4789ca473d8 · outbound

This paper cites Cosmopedia, February 2024.

Hardware-Efficient Attention for Fast Decoding Cosmopedia, February 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.606445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52226de7-e862-4371-ba00-cd0cd4de1039 · outbound

This paper cites PIQA : reasoning about physical commonsense in natural language.

Hardware-Efficient Attention for Fast Decoding PIQA : reasoning about physical commonsense in natural language

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.689226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b89d84-b0e0-4fb9-b254-9faf7d4b55d3 · outbound

This paper cites GPT-NeoX-20B: An Open-Source Autoregressive Language Model.

Hardware-Efficient Attention for Fast Decoding GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.758624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd97bfa7-81dd-4579-b112-b259b2a85479 · outbound

This paper cites Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.

Hardware-Efficient Attention for Fast Decoding Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.855424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6dc91aa-aca2-434d-bc3b-409bccdb244c · outbound

This paper cites Language Models are Few-Shot Learners.

Hardware-Efficient Attention for Fast Decoding Language Models are Few-Shot Learners

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.964527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5ea5fb-a49e-40fb-b73a-2d4c9cb73d6a · outbound

This paper cites Palu: Compressing KV-Cache with Low-Rank Projection.

Hardware-Efficient Attention for Fast Decoding Palu: Compressing KV-Cache with Low-Rank Projection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.031025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd2ed83-9ca6-45b0-9e61-9a775d604bad · outbound

This paper cites What rotary position embedding can tell us: Identifying query and key weights corresponding to basic syntactic or high-level semantic information.

Hardware-Efficient Attention for Fast Decoding What rotary position embedding can tell us: Identifying query and key weights corresponding to basic syntactic or high-level semantic information

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.124285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1256f6-b547-4074-af20-9c032096d05d · outbound

This paper cites MagicPIG: LSH Sampling for Efficient LLM Generation.

Hardware-Efficient Attention for Fast Decoding MagicPIG: LSH Sampling for Efficient LLM Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.213422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7ee620-6b3d-4922-8314-c5a0505f2535 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Hardware-Efficient Attention for Fast Decoding FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.282299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95c9086a-1c49-4563-97dd-31c451a00e4d · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Hardware-Efficient Attention for Fast Decoding Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.361518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c6219a-08ae-40e7-996d-9744c11d397f · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

Hardware-Efficient Attention for Fast Decoding FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.427540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7970ad1-5764-47cf-ab55-18c67e2fed42 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Hardware-Efficient Attention for Fast Decoding DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.499057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e5787e-a7a4-4627-a326-c57ad1e02fa2 · outbound

This paper cites DeepSeek-V3 Technical Report.

Hardware-Efficient Attention for Fast Decoding DeepSeek-V3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.545757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7968316b-9305-4349-8005-76947f67185c · outbound

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

Hardware-Efficient Attention for Fast Decoding DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.660022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8ea07b-7e80-4384-8a62-49119f32b53c · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Hardware-Efficient Attention for Fast Decoding The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.694921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139f2bc8-0929-4599-b437-cfbf0a2f0cfd · outbound

This paper cites AI and Memory Wall.

Hardware-Efficient Attention for Fast Decoding AI and Memory Wall

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.729115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff636470-7567-4fcc-aacd-2e29786a2d98 · outbound

This paper cites What Your DRAM Power Models Are Not Telling You: Lessons from a Detailed Experimental Study.

Hardware-Efficient Attention for Fast Decoding What Your DRAM Power Models Are Not Telling You: Lessons from a Detailed Experimental Study

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:32:36.701141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d741e4a5-9158-4ac3-a163-4c04e4e0f317 · outbound

This paper cites Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA.

Hardware-Efficient Attention for Fast Decoding Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.813413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c615176-c5f5-4637-b98a-a7516149c1d0 · outbound

This paper cites The Llama 3 Herd of Models.

Hardware-Efficient Attention for Fast Decoding The Llama 3 Herd of Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.846409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2955cf70-99a0-4063-95b3-5f8086e443cc · outbound

This paper cites an unresolved cited work.

Hardware-Efficient Attention for Fast Decoding Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:32:39.162151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9f7dd2d3-10c8-40d3-a70c-dec91328cd2a · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Hardware-Efficient Attention for Fast Decoding Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.925220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f576932a-1cf8-4630-82db-d0af173eecb0 · outbound

This paper cites FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines.

Hardware-Efficient Attention for Fast Decoding FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.932279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 944ab807-ae86-4bad-a3b8-b1eb23e8c927 · outbound

This paper cites Measuring massive multitask language understanding.

Hardware-Efficient Attention for Fast Decoding Measuring massive multitask language understanding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.970755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b846c7a3-8c26-4820-9f30-fd34b7596dbf · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

Hardware-Efficient Attention for Fast Decoding KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.954664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52e12996-15d3-485f-bf64-f646d8edfe21 · outbound

This paper cites Multi-matrix Factorization Attention.

Hardware-Efficient Attention for Fast Decoding Multi-matrix Factorization Attention

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:32:36.488542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1be02b3e-8259-4ea6-94a7-4198e332a6e4 · outbound

This paper cites Data Movement Is All You Need: A Case Study on Optimizing Transformers.

Hardware-Efficient Attention for Fast Decoding Data Movement Is All You Need: A Case Study on Optimizing Transformers

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.978625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bfcb9ad-1b43-4722-8b3f-0c50f89efe30 · outbound

This paper cites Towards economical inference: Enabling deepseek's multi-head latent attention in any transformer-based llms, 2025.

Hardware-Efficient Attention for Fast Decoding Towards economical inference: Enabling deepseek's multi-head latent attention in any transformer-based llms, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:30.994451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f0562a-5d2d-4c4f-aa66-386544c71ac7 · outbound

This paper cites Weight decay induces low-rank attention layers.

Hardware-Efficient Attention for Fast Decoding Weight decay induces low-rank attention layers

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.007337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 661446ef-c137-4989-9696-e2e1da24b08f · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Hardware-Efficient Attention for Fast Decoding Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.026027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21995711-3da1-4c6a-8a20-0e9cfaadaa91 · outbound

This paper cites Software pipelining: An effective scheduling technique for vliw machines.

Hardware-Efficient Attention for Fast Decoding Software pipelining: An effective scheduling technique for vliw machines

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.784872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f71a8029-0f86-4186-8e08-25c87f10d93e · outbound

This paper cites Flashmla: Efficient mla decoding kernels.

Hardware-Efficient Attention for Fast Decoding Flashmla: Efficient mla decoding kernels

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.627480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation eff9c8b8-d14c-434b-b783-8a38e6bee5b5 · outbound

This paper cites PyTorch Distributed: Experiences on Accelerating Data Parallel Training.

Hardware-Efficient Attention for Fast Decoding PyTorch Distributed: Experiences on Accelerating Data Parallel Training

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.080828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4c7db0-b686-4cbb-8373-b9af37adc193 · outbound

This paper cites Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models.

Hardware-Efficient Attention for Fast Decoding Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.119922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f701fc1d-ca5f-4519-8b73-65db4e436b18 · outbound

This paper cites Decoupled Weight Decay Regularization.

Hardware-Efficient Attention for Fast Decoding Decoupled Weight Decay Regularization

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.164678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503095d2-ec09-4a0f-a98b-a455f59f9589 · outbound

This paper cites Fineweb-edu: The finest collection of educational content, 2024.

Hardware-Efficient Attention for Fast Decoding Fineweb-edu: The finest collection of educational content, 2024

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.436599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 638a7032-594d-4b74-9745-4f0ad845af01 · outbound

This paper cites TransMLA: Multi-Head Latent Attention Is All You Need.

Hardware-Efficient Attention for Fast Decoding TransMLA: Multi-Head Latent Attention Is All You Need

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.245399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8135a6be-8134-4eaf-b8c6-15fbe0896b87 · outbound

This paper cites The Llama 4 Herd: The Beginning of a New Era of Natively Multimodal AI Innovation , 2025.

Hardware-Efficient Attention for Fast Decoding The Llama 4 Herd: The Beginning of a New Era of Natively Multimodal AI Innovation , 2025

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.252804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 09bf71be-fb68-43d3-8ab1-3211e8692aa4 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

Hardware-Efficient Attention for Fast Decoding Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.323457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c0562cb-be3a-4f63-ab2d-2bbf53aedc0b · outbound

This paper cites Orca: Progressive Learning from Complex Explanation Traces of GPT-4.

Hardware-Efficient Attention for Fast Decoding Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.382482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b98d2e69-c40f-4c0f-a376-a80a2b2b4410 · outbound

This paper cites Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM.

Hardware-Efficient Attention for Fast Decoding Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.424098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0e748c-836d-45c4-a33c-a574081d2c92 · outbound

This paper cites NVIDIA H100 tensor core gpu architecture.

Hardware-Efficient Attention for Fast Decoding NVIDIA H100 tensor core gpu architecture

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:38.088689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5d24c8e9-66ce-43f3-ae8d-bca541d95507 · outbound

This paper cites NVIDIA Blackwell architecture technical brief.

Hardware-Efficient Attention for Fast Decoding NVIDIA Blackwell architecture technical brief

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.939319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ad2625d0-5d63-4535-ab96-701d522e82d1 · outbound

This paper cites Nvlink, 2024.

Hardware-Efficient Attention for Fast Decoding Nvlink, 2024

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.755767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 96183437-57c5-4352-a08c-630affcfbdf6 · outbound

This paper cites Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library.

Hardware-Efficient Attention for Fast Decoding Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:32:36.174838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2915d83a-6956-42af-aa26-f424888facb7 · outbound

This paper cites OpenAI o1 System Card.

Hardware-Efficient Attention for Fast Decoding OpenAI o1 System Card

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.887862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1702db5c-1acd-43d7-b486-f84714a7ed3b · outbound

This paper cites Efficiently Scaling Transformer Inference.

Hardware-Efficient Attention for Fast Decoding Efficiently Scaling Transformer Inference

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.926378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bcb144d-aa00-4007-b461-f4a2a6e581ba · outbound

This paper cites Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference.

Hardware-Efficient Attention for Fast Decoding Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:31.995104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788ca0a5-0716-46b8-891c-d7d56a934921 · outbound

This paper cites Winogrande : An adversarial winograd schema challenge at scale.

Hardware-Efficient Attention for Fast Decoding Winogrande : An adversarial winograd schema challenge at scale

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.608442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ead51bd7-7598-479f-a897-c57912814f90 · outbound

This paper cites Eigen Attention: Attention in Low-Rank Space for KV Cache Compression.

Hardware-Efficient Attention for Fast Decoding Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.138676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3fdf22-8490-4f41-8d96-586d4a78f0f0 · outbound

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

Hardware-Efficient Attention for Fast Decoding Flashattention-3: Fast and accurate attention with asynchrony and low-precision

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.483734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6f1e4605-2836-4295-a4ac-b2b98d1da2b0 · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

Hardware-Efficient Attention for Fast Decoding FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.266167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5b00151-640b-42bb-9877-83f742b3eea4 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Hardware-Efficient Attention for Fast Decoding Fast Transformer Decoding: One Write-Head is All You Need

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.363913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62940194-287f-414c-bdc0-0abb9eb19d8f · outbound

This paper cites FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU.

Hardware-Efficient Attention for Fast Decoding FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.440200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5adf0400-21db-4fc6-8c8a-0c87a08d3785 · outbound

This paper cites Loki: Low-rank Keys for Efficient Sparse Attention.

Hardware-Efficient Attention for Fast Decoding Loki: Low-rank Keys for Efficient Sparse Attention

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.523852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5153ecd2-bccb-4103-b046-66d22c674311 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Hardware-Efficient Attention for Fast Decoding Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.582152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19705616-bf2d-4dd9-9de1-b0e7f5552dd9 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Hardware-Efficient Attention for Fast Decoding RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.701752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97826bf4-382f-47e4-a23f-1c48ba6253a6 · outbound

This paper cites Seesaw: High-throughput LLM Inference via Model Re-sharding.

Hardware-Efficient Attention for Fast Decoding Seesaw: High-throughput LLM Inference via Model Re-sharding

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.805859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2393bfa6-f739-4a74-81c7-0b8bee2b5202 · outbound

This paper cites ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference.

Hardware-Efficient Attention for Fast Decoding ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:32.885907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d19750-7ca1-40a7-8855-f457f13434a0 · outbound

This paper cites CUTLASS , January 2023.

Hardware-Efficient Attention for Fast Decoding CUTLASS , January 2023

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.348425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d1c09476-aaa9-4969-8441-a25821869572 · outbound

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

Hardware-Efficient Attention for Fast Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.058043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24488eff-f07b-4f01-9b36-09c7b3a08eb1 · outbound

This paper cites Attention is all you need.

Hardware-Efficient Attention for Fast Decoding Attention is all you need

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.173385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d11f10f8-e395-435c-9a61-dbafc7f0840d · outbound

This paper cites Gpt-j-6b: a 6 billion parameter autoregressive language model, 2021.

Hardware-Efficient Attention for Fast Decoding Gpt-j-6b: a 6 billion parameter autoregressive language model, 2021

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:37.172316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e15629f2-7a49-41eb-85b5-df5ef3621fc5 · outbound

This paper cites RedPajama: an Open Dataset for Training Large Language Models.

Hardware-Efficient Attention for Fast Decoding RedPajama: an Open Dataset for Training Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.391740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c4e85d-efab-4fde-a5a5-a4e3263c2ed7 · outbound

This paper cites Crowdsourcing Multiple Choice Science Questions.

Hardware-Efficient Attention for Fast Decoding Crowdsourcing Multiple Choice Science Questions

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.520521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e3223e-4804-4ed6-bc09-e0459f95b255 · outbound

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

Hardware-Efficient Attention for Fast Decoding Roofline: an insightful visual performance model for multicore architectures

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.655981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692ab0ed-be0c-493f-b724-84e4e1f72e74 · outbound

This paper cites LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding.

Hardware-Efficient Attention for Fast Decoding LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.762529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9110ff98-fbaa-4836-9a8b-59490b1c9cd7 · outbound

This paper cites Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation.

Hardware-Efficient Attention for Fast Decoding Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.884257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d6193d9-49dc-49f7-887e-729b9f1582cb · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Hardware-Efficient Attention for Fast Decoding Efficient Streaming Language Models with Attention Sinks

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:33.994365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9dcf9c-f951-456e-8398-1e779737b3f8 · outbound

This paper cites Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering.

Hardware-Efficient Attention for Fast Decoding Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.109663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6fa272e-353d-4eda-b049-f0269a2789eb · outbound

This paper cites Rope to nope and back again: A new hybrid attention strategy, 2025.

Hardware-Efficient Attention for Fast Decoding Rope to nope and back again: A new hybrid attention strategy, 2025

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.255027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8006c060-ad31-4f82-9c8d-43160b9684fa · outbound

This paper cites Gated Linear Attention Transformers with Hardware-Efficient Training.

Hardware-Efficient Attention for Fast Decoding Gated Linear Attention Transformers with Hardware-Efficient Training

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.407299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5467938-fa24-4ea2-884c-4e003de5fc59 · outbound

This paper cites Effectively Compress KV Heads for LLM.

Hardware-Efficient Attention for Fast Decoding Effectively Compress KV Heads for LLM

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.524396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8762b690-7f6b-45bc-9cdc-fcf2bc0739ca · outbound

This paper cites Affordable Generative Agents.

Hardware-Efficient Attention for Fast Decoding Affordable Generative Agents

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.655835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65eb3793-a028-4e6d-9bba-e34299118ba5 · outbound

This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.

Hardware-Efficient Attention for Fast Decoding Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.791543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a7190d-872d-4076-96af-5d8ba2eb9908 · outbound

This paper cites HellaSwag : Can a machine really finish your sentence? In Anna Korhonen, David R.

Hardware-Efficient Attention for Fast Decoding HellaSwag : Can a machine really finish your sentence? In Anna Korhonen, David R

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:34.945787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58724d79-09c6-4ab7-8ef7-da461af97e40 · outbound

This paper cites Tensor product attention is all you need, 2025.

Hardware-Efficient Attention for Fast Decoding Tensor product attention is all you need, 2025

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:35.042714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b36fd59c-01be-41ec-84e9-33fb8e59e3e3 · outbound

This paper cites H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

Hardware-Efficient Attention for Fast Decoding H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:35.147561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2144f0f0-0145-4270-afb6-4cc0b32e59be · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

Hardware-Efficient Attention for Fast Decoding SGLang: Efficient Execution of Structured Language Model Programs

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:35.275765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 830b33b4-b87e-4a4d-a26e-bfd33221fa38 · outbound

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

Hardware-Efficient Attention for Fast Decoding Sglang: Efficient execution of structured language model programs

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:32:36.995246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation 5f4dc038-a52c-45e7-8213-b076abe14c63 · inbound

TransMLA: Multi-Head Latent Attention Is All You Need cites this paper.

TransMLA: Multi-Head Latent Attention Is All You Need Hardware-Efficient Attention for Fast Decoding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T11:48:01.180107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 292cce17-8c9a-4178-887e-7497c8c511e0 · inbound

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning cites this paper.

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning Hardware-Efficient Attention for Fast Decoding

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T05:06:32.737715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a655ef5-cf0b-481a-a0e3-b783519b25c6 · inbound

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference cites this paper.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Hardware-Efficient Attention for Fast Decoding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.095113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97ed32f-bce7-49e3-9860-9a60cc640eea · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Hardware-Efficient Attention for Fast Decoding

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:45:40.085058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bc4302b9-6ff6-4770-8263-b52508b85bad · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Hardware-Efficient Attention for Fast Decoding

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-11T01:57:51.357138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.