Paper Citation Record · LEDGER

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

As of 13 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 2 inbound Pith citation observations for arXiv:2602.10718.

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

pith.paper-citation-record.v1
2602.10718 v3

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T05:58:03.113220Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:17:09.834609Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T21:26:16.418821Z

Reference resolution

48 of 48 outbound references displayed

verified exact28
verified fuzzy14
unresolved1
parse uncertain3
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ff04e2b7-85ac-4e7e-834c-bf1ce329ac26 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.740867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d24bc5db-c3dd-4b34-b259-5aaf256ee9a0 · outbound

This paper cites DeepSeek-V3 Technical Report.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining DeepSeek-V3 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.737232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9de1798a-32a1-499c-b0bb-e358b6d830b7 · outbound

This paper cites Large language models: a survey of their development, capabilities, and applications.Knowledge and Information Systems, 67(3):2967–3022.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Large language models: a survey of their development, capabilities, and applications.Knowledge and Information Systems, 67(3):2967–3022

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.412001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2e41304e-2d6e-4cb2-9134-275e1cd61209 · outbound

This paper cites Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213– 100240.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213– 100240

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.409792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e339cbd7-a8b8-4fcd-b620-23eb6c459b6d · outbound

This paper cites Beyondaime: Advancing math reasoning evaluation beyond high school olympiads.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Beyondaime: Advancing math reasoning evaluation beyond high school olympiads

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.405607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation da9fac27-60df-462d-9c09-4df9712bedd9 · outbound

This paper cites Kvquant: Towards 10 million context length llm inference with kv cache quantization.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Kvquant: Towards 10 million context length llm inference with kv cache quantization

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.407669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b2c2e177-53a5-465e-ba1f-1eb02c3c8643 · outbound

This paper cites Introducing LongCat-flash-thinking: A technical report.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Introducing LongCat-flash-thinking: A technical report

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.708301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d3cd48a7-b0a4-4fed-8418-f758da0887c4 · outbound

This paper cites Longcat-flash technical report.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Longcat-flash technical report

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.705131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation eb96c667-edaf-44f5-8f66-4620ccfbe884 · outbound

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

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.807482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f4d28fa1-cf1e-4b17-a6f4-5dbde74f30ac · outbound

This paper cites Are We Done with MMLU?.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Are We Done with MMLU?

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.711571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1396979d-481e-4421-9d02-8e322cfc130d · outbound

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

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.733974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0c31b9a6-c1d5-433a-bc64-53ff67c91f19 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Measuring Massive Multitask Language Understanding

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.724731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 028ebe34-3e9b-4e94-8cd5-cc8794a6c64a · outbound

This paper cites Hmmt 2025.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Hmmt 2025

Reference 13

Resolution: parse uncertain; raw_fallback, observed 2026-05-16T06:00:41.442481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a6e294eb-2d6f-4672-8ed3-0e82722d1d48 · outbound

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

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Flashattention-3: Fast and accurate attention with asyn- chrony and low-precision

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.440548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b8e00ad6-46fa-4c02-8815-fdad04cf581f · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.438225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a8bdbf34-4915-4981-bc9b-9fbf9317e9ef · outbound

This paper cites Flashmla: Efficient multi-head latent attention kernels.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Flashmla: Efficient multi-head latent attention kernels

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.435586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bd162b2c-62f9-4ba4-b5a4-eefdb6b46a4d · outbound

This paper cites Fp8 quantization: The power of the exponent.Advances in Neural Information Processing Systems, 35:14651–14662.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Fp8 quantization: The power of the exponent.Advances in Neural Information Processing Systems, 35:14651–14662

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.432977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a10f8116-8746-4f62-9278-ea6d0cbfeaec · outbound

This paper cites A Survey on Large Language Model Acceleration based on KV Cache Management.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining A Survey on Large Language Model Acceleration based on KV Cache Management

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.800812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ea2e2da1-6c11-417a-ab5c-00f035b25fcf · outbound

This paper cites FPTQ: Fine-grained Post-Training Quantization for Large Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining FPTQ: Fine-grained Post-Training Quantization for Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.790664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ffb43ce5-0f4b-4e5c-bb04-6d0b42bb1dfa · outbound

This paper cites From live data to high-quality benchmarks: The arena-hard pipeline, April 2024.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining From live data to high-quality benchmarks: The arena-hard pipeline, April 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.430158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 146f8d88-3c75-485b-a414-89bae5b4080d · outbound

This paper cites Let’s verify step by step.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Let’s verify step by step

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.427723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation afd98214-88a5-4ff9-bb3d-3162a0aff120 · outbound

This paper cites Zebralogic: On the scaling limits of LLMs for logical reasoning.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Zebralogic: On the scaling limits of LLMs for logical reasoning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.425299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 85a44771-7cbb-4e45-8c06-ce93a4e8cbe8 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of machine learning and systems, 6:87–100.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of machine learning and systems, 6:87–100

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.422560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b96e52ad-ce14-4acb-ae21-6e69344598f3 · outbound

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

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.787332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c9283ccc-49a4-4505-9a65-f03811395bf1 · outbound

This paper cites & Cai, X.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining & Cai, X

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:00:40.727875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 401b5094-ff2a-45d5-863a-4030a33e5ac6 · outbound

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

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.714918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c87961f7-0b14-4ef1-a1e1-fabfdb25302b · outbound

This paper cites Aime 2024.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Aime 2024

Reference 27

Resolution: parse uncertain; raw_fallback, observed 2026-05-16T06:00:41.420002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6406654b-3f19-44e9-a286-6746a9842724 · outbound

This paper cites Aime 2025.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Aime 2025

Reference 28

Resolution: parse uncertain; raw_fallback, observed 2026-05-16T06:00:41.418155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a8535f93-a846-44a7-8091-26e1744cc9b0 · outbound

This paper cites Nvidia h100 tensor core gpu.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Nvidia h100 tensor core gpu

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.444489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 28da0d75-5e81-4a14-899e-9f53e5f184c9 · outbound

This paper cites FP8 Formats for Deep Learning.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining FP8 Formats for Deep Learning

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.780835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 872555fd-866a-4059-a8c7-45b562dca162 · outbound

This paper cites an unresolved cited work.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-16T06:00:41.416066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b21af5fd-a71a-4e57-a297-453a0d1f8cd8 · outbound

This paper cites Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.765255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 738d38ad-17eb-4351-93ff-6eef95345c56 · outbound

This paper cites Unveiling super experts in mixture-of-experts large language models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Unveiling super experts in mixture-of-experts large language models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.769142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 75706047-98c0-465f-8482-4571787ff875 · outbound

This paper cites AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.761408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 941a7b1b-0002-4dab-a2d8-811c82e3db2e · outbound

This paper cites KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.756876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ffc5e7d6-2ead-4d3b-9349-b6a1fc54ba35 · outbound

This paper cites Massive Activations in Large Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Massive Activations in Large Language Models

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-16T07:02:54.298502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 19de3124-d426-40e6-bb7f-00ec675e5497 · outbound

This paper cites Longcat-flash-thinking-2601 technical report.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Longcat-flash-thinking-2601 technical report

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.772983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8115f59e-59db-4dfd-a92f-2a0e67652181 · outbound

This paper cites Longcat-flash-omni technical report.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Longcat-flash-omni technical report

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.784126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2181953e-4a3c-40af-bae4-5cebd2f7a20d · outbound

This paper cites FP8 versus INT8 for efficient deep learning inference.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining FP8 versus INT8 for efficient deep learning inference

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:00:40.804585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ab9cbd9a-41aa-410b-9fb2-8beda59b1d44 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.744485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4b5203a8-14c2-436b-bcdc-0a352b55ec5c · outbound

This paper cites Exploring layer-wise information effectiveness for post-training quantization in small language models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Exploring layer-wise information effectiveness for post-training quantization in small language models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.794189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8aa1dece-69ae-4dec-b02c-f03492ae9dd6 · outbound

This paper cites Dope: Denoising rotary position embedding.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Dope: Denoising rotary position embedding

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.752336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 818aac3d-4993-424f-b1dc-d899ec3280d3 · outbound

This paper cites ParallelComp: Parallel Long-Context Compressor for Length Extrapolation.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.721817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e33aaf71-3a38-47ba-93a8-a839b1471656 · outbound

This paper cites Fit and prune: Fast and training-free visual token pruning for multi-modal large language models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Fit and prune: Fast and training-free visual token pruning for multi-modal large language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T06:00:41.414152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e8c23886-9869-4f6f-8177-b2cb59ef9e6e · outbound

This paper cites RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.748727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cfd79c3e-131e-4582-9060-99f4ad02e374 · outbound

This paper cites Efficient context scaling with longcat zigzag attention.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Efficient context scaling with longcat zigzag attention

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:00:40.797923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation db7c344a-33ed-4e21-bf4a-efeaf9d8d115 · outbound

This paper cites Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.730979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c10a3a8d-699b-4888-b2ff-d0a95b7cebf2 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Instruction-Following Evaluation for Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.718108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation 1f507c2f-d205-4357-bc1c-f7dd9b5705f1 · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:05:58.161185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c274f7cc-b4a6-4258-a008-fa485603c4dd · inbound

Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving cites this paper.

Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:26:16.431880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.