Paper Citation Record · LEDGER

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

As of 8 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 3 inbound Pith citation observations for arXiv:2508.15881.

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

pith.paper-citation-record.v1
2508.15881 v2

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:55:12.532975Z

measured 66 of 66 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T17:32:37.642188Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-11T01:57:51.549825Z

Reference resolution

63 of 63 outbound references displayed

verified exact10
verified fuzzy7
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6edc2b6b-c2c2-4309-9ccc-ad3b0e024c57 · outbound

This paper cites Hello GPT-4o, 2024.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Hello GPT-4o, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:05.969609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa797d20-45f1-49d0-a11c-81497eb6b47f · outbound

This paper cites Claude 3.5 sonnet, 2024.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Claude 3.5 sonnet, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.070966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965d0c1e-df52-49f4-ba11-53487b71ee5c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.170024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f5385e1-57fc-40a2-9fbf-8c44ec7646e5 · outbound

This paper cites Improving language understanding by generative pre-training.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Improving language understanding by generative pre-training

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.200705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340b23cc-06af-434f-8069-893f1b047482 · outbound

This paper cites Language models are few-shot learners.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Language models are few-shot learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.281785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f929d593-9219-4713-9a8b-eef18834e01c · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Palu: Compressing KV-Cache with Low-Rank Projection

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.348432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec240f3a-ad6f-416e-a183-1e108f27f7a8 · outbound

This paper cites xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.405836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a51bea7-5360-48d8-995f-7b83e8aec3b8 · outbound

This paper cites Transformers are Multi-State RNNs.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Transformers are Multi-State RNNs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.525852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7d8e1c-4d26-40de-a192-56676940206f · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.637672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d7552b-b5c9-49af-b04f-21d5462056a3 · outbound

This paper cites Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:06.756104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9e895fb-9fb8-4df6-b298-9f9d347da560 · outbound

This paper cites SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:15.253571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d5560a2c-a598-4adb-8bf2-445f2ebf7791 · outbound

This paper cites Tensor-parallelism with partially synchronized activations.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Tensor-parallelism with partially synchronized activations

Reference 12

Resolution: verified exact; raw_fallback, observed 2026-08-05T17:55:14.958729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cdaf4a06-f029-4ae2-8f28-43a37df27a65 · outbound

This paper cites Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.138663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90d1014f-f333-4cb1-9c37-0284d893ebb7 · outbound

This paper cites Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.250063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e348d791-4afe-4c49-ae5b-11306a7fa47e · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.365952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63dff6cf-7348-463e-be2b-411436252875 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference TransMLA: Multi-Head Latent Attention Is All You Need

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.508723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 975fa342-94ee-49e6-911b-192190c4e5a3 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.673578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0065ab31-3123-4b57-b276-47b67095ef55 · outbound

This paper cites Llama 3 model card, 2024.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Llama 3 model card, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.854166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c7fda1-37fe-49d8-a9a4-a5142ac201f7 · outbound

This paper cites DeepSeek-V3 Technical Report.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference DeepSeek-V3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:07.985138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Hardware-Efficient Attention for Fast Decoding.

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 bf4903d4-8734-4d1d-8c41-e98c273649d9 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.179444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb8e1ff1-35dd-4b7e-bb30-414854bdeb30 · outbound

This paper cites DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.261078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74ef57b3-bd3a-4e58-9d51-25808beb877d · outbound

This paper cites CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.361255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c6fd89-3438-408f-9755-0f5b15e2ed3f · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference SnapKV: LLM Knows What You are Looking for Before Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.477550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7ec6af8-00c3-42e1-aba7-a1a71f7b5545 · outbound

This paper cites LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.556414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9828a0e-fcb4-4bdf-be76-030d6eaa0a87 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.677974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b418c4-ede0-4354-bc8b-8640b51de096 · outbound

This paper cites Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.753827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f9f956-7c89-4b28-920a-cdc8de6a3b42 · outbound

This paper cites Zsmerge: Zero-shot kv cache compression for memory-efficient long-context llms.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Zsmerge: Zero-shot kv cache compression for memory-efficient long-context llms

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:08.857090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f168205e-0307-4026-8c99-cef1defffce9 · outbound

This paper cites Efficient long-context llm inference via kv cache clustering.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Efficient long-context llm inference via kv cache clustering

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-05T17:55:14.366584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d040f08-9e60-418b-ae63-6fe5022c1419 · outbound

This paper cites KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.149968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0279807a-455a-42b3-9ac9-00da505464b2 · outbound

This paper cites Inference-Friendly Models With MixAttention.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Inference-Friendly Models With MixAttention

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:14.064205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60be5ed8-16ce-4a7e-941f-1cd3df3493bf · outbound

This paper cites Layer-Condensed KV Cache for Efficient Inference of Large Language Models.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Layer-Condensed KV Cache for Efficient Inference of Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.408451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e62bd1eb-86d9-4cb8-8820-9fec1ed413d2 · outbound

This paper cites A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:13.833354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6d5022ab-4df1-4ddb-b02e-098ef4e89e67 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.661574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c0fb4e1-5587-4190-a412-ac69e2e71b3b · outbound

This paper cites LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.743965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2434c60e-8e4b-408c-8625-af96bc073b3c · outbound

This paper cites MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.824153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 129d056b-aa76-4449-8ef0-fd01fe67112e · outbound

This paper cites Effectively Compress KV Heads for LLM.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Effectively Compress KV Heads for LLM

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.928919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30df9cd3-da21-4b66-94cc-6e529e1f16c4 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.035877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406bcb6e-4a11-4d5f-a52a-d2c81af75543 · outbound

This paper cites MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:13.570436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4e4f6c27-5b95-414c-8f31-40f5ea2c1fff · outbound

This paper cites QAQ: Quality Adaptive Quantization for LLM KV Cache.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference QAQ: Quality Adaptive Quantization for LLM KV Cache

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.297309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06792c92-3127-4413-b66c-d107532327c0 · outbound

This paper cites TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:13.365091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 06455c16-75ee-45b9-a55e-80ba7532ad83 · outbound

This paper cites Large scale distributed deep networks.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Large scale distributed deep networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.478577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ed51e7b-2b70-4475-a962-b76d80725d2e · outbound

This paper cites Horovod: fast and easy distributed deep learning in TensorFlow.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Horovod: fast and easy distributed deep learning in TensorFlow

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.614756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1925cf9e-10c1-4370-867c-5a8b2a871581 · outbound

This paper cites Gpipe: Efficient training of giant neural networks using pipeline parallelism.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Gpipe: Efficient training of giant neural networks using pipeline parallelism

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.743554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7396cf27-1e60-4aa8-96ba-124365c1f946 · outbound

This paper cites Pipedream: Generalized pipeline parallelism for dnn training.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Pipedream: Generalized pipeline parallelism for dnn training

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.818690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69d8ba3e-4312-4cc6-a132-ffc9930d9915 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:10.957633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1771d614-49e7-4410-b557-3a488ece433a · outbound

This paper cites An Efficient 2D Method for Training Super-Large Deep Learning Models.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference An Efficient 2D Method for Training Super-Large Deep Learning Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:13.186945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 16c73e13-a6d2-4f21-b730-3382a05f53b1 · outbound

This paper cites Maximizing Parallelism in Distributed Training for Huge Neural Networks.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Maximizing Parallelism in Distributed Training for Huge Neural Networks

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:13.001003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dc945350-74c7-40d7-a7fe-22216310527c · outbound

This paper cites Sequence Parallelism: Long Sequence Training from System Perspective.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Sequence Parallelism: Long Sequence Training from System Perspective

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:11.234042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ef7060-1cc4-4fb6-a21a-afd6fa062cb5 · outbound

This paper cites NVIDIA dynamo, a low-latency distributed inference framework for scaling reasoning ai models.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference NVIDIA dynamo, a low-latency distributed inference framework for scaling reasoning ai models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:16.949194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0ef47a78-7883-4088-bfe2-a993c0cb07fa · outbound

This paper cites Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM Serving.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM Serving

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-05T17:55:12.797644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5ae5a0c8-de1c-46c6-ae05-062650b6c4ca · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference {DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:11.497826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bb093de-5471-4821-a6ec-228d975ac973 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:11.586104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1dab253-a3ef-4535-9418-2b625967db27 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Kimi K2: Open Agentic Intelligence

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:11.656509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986acead-968f-4d81-a5cd-48dded46847d · outbound

This paper cites Mea- suring massive multitask language understanding.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Mea- suring massive multitask language understanding

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:16.735462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62c1e467-c512-4891-a383-774e9c6755cc · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:11.883455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce74745c-520b-4f95-a0a1-213aede0a115 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference PIQA: reasoning about physical commonsense in natural language

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:16.503922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8dfad646-0691-4224-80fa-631e4c3e4c13 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Hellaswag: Can a machine really finish your sentence? In Anna Korhonen, David R

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:16.307242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a14dcce-2508-4c20-9d78-59ed1a8a7e84 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Can a suit of armor conduct electricity? A new dataset for open book question answering

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:16.074606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f753b1f5-1f3a-4978-ae79-f8259aa643e9 · outbound

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

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Winogrande: an adversarial winograd schema challenge at scale

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:15.841490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e9d15e7c-55ff-4312-b58a-8c29caef111c · outbound

This paper cites Pointer sentinel mixture models, 2016.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Pointer sentinel mixture models, 2016

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:12.333239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bcaf792-9df4-4cac-a2a0-7e6b2e80661b · outbound

This paper cites Smollm-corpus.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Smollm-corpus

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:55:15.579058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 150c8a9f-d5b0-4fb1-9061-5f6866b520a0 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:12.532975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bb906a33-09fe-4c7b-bf98-729123df890d · 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 TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:45:40.138975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f560a902-6b34-41e3-84c4-5b085714bdde · 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 TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-11T01:57:51.582428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6107027a-ed16-41c6-ab09-fbc260fc3daa · inbound

A Training-Memory Regression in MLA Sequence Parallelism: Why Megatron-Core Forbids Absorption, and LAGA -- a Communication-Efficient Fix cites this paper.

A Training-Memory Regression in MLA Sequence Parallelism: Why Megatron-Core Forbids Absorption, and LAGA -- a Communication-Efficient Fix TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T17:32:37.642188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.