Pith. sign in

Paper Citation Record · LEDGER

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching

As of 13 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2608.08097.

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

pith.paper-citation-record.v1
2608.08097 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:32:37.769236Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

49 of 49 outbound references displayed

  • verified exact5
  • verified fuzzy4
  • unresolved36
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation af0bf56f-bea9-4b5e-a05b-06bc139976ee · outbound

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

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.548174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.548174Z digest=sha256:f0ac8a324edcabd22a8fab70ada26866e3f70b3813d416b23f000269479324c6

Observation 937ab863-a18a-42ae-a550-4a1027d23276 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.090364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.553554Z digest=sha256:477e637462c376b11ed98b47b8bac87596b09110efc1922f58b85f8e32a26f87

Observation 6eac5927-acb2-444f-ae13-9fd74da242e5 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 3

Resolution
malformed identifier
doi_truncated, observed 2026-08-12T00:32:38.764098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.558655Z digest=sha256:6387069ac7acf6b5c9b3906eed65e9944eeec757503f82f39191635c30e46dcc

Observation 91792a2e-9c4e-4213-aa3f-fc6d13aa6f0e · outbound

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

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.563550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.563550Z digest=sha256:4d890778ffb3186437a11553f4763011cfa4207fa8eee5c093fc12aa25bdb94f

Observation ccc1fac3-887d-4ef5-876f-b9b69b509e7b · outbound

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

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.568595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.568595Z digest=sha256:ad7e59b6dd4dfa5c4ca53c1f1ced08e832625e77cf292b580a44eecc13ae48a1

Observation c7e8b1f0-4b3d-4ecb-a5e3-9373abf35d6f · outbound

This paper cites Hendryx, Zifan Wang, Chen Bo Calvin Zhang, Noah Jacobson, Bing Liu, and Brad Kenstler.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Hendryx, Zifan Wang, Chen Bo Calvin Zhang, Noah Jacobson, Bing Liu, and Brad Kenstler

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:32:39.076004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.573482Z digest=sha256:baae1f0d963278f4449c9b8edaf785e385975955002487a8fcb97dbcae169c92

Observation 8eac5092-a1c1-407b-8f13-ce05c7903430 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.061475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.578640Z digest=sha256:e08105da5656bc60837ccc765265bd103867a0090f57299c7ba1bfc6d26a19b6

Observation 38edf940-1fcd-4116-8a21-b25c5827e5e4 · outbound

This paper cites SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.587787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.587787Z digest=sha256:4195328c99132b55a199fe483f8df76ab6b16e948f8df08d24586b1162a1d86f

Observation a018605d-1938-4fb8-81b5-005e03e0d0c1 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.047160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.592360Z digest=sha256:58ac10be5ec11ff9301a4d788e72ccd59ca7ed4e60d475dae4ebbcdf3e809326

Observation 2c61d42a-e2bd-4aaa-b41d-f29dfa8b0c6f · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.032925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.596804Z digest=sha256:d630740272e00d8c12794aaa8256aa1fae5af669ae755150dd21debdb3f98b3c

Observation ac14ab7f-d113-4e76-9b76-816b3b767422 · outbound

This paper cites MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.605595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.605595Z digest=sha256:7c8a34a10863fd010efc5264da2f72f6464c7939ec88c926182e33f14321786b

Observation 8c68286f-d414-45b1-8740-242bdbc633fd · outbound

This paper cites EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction

Reference 12

Resolution
metadata mismatch
local_arxiv, observed 2026-08-12T00:32:38.599090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.600976Z digest=sha256:6d0ad579238162cff9a77f84e25e22593bc09af330d61c9c04c26e511f819e40

Observation 78017947-a256-42b2-af92-388ef4ebc6e2 · outbound

This paper cites FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.614058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.614058Z digest=sha256:99f52976ec5efa4aa9bf29a4fbc95c7c7df3fc37664705ded205a7f47155d915

Observation 8d9f0df2-b4ba-4e0c-b6ac-3093900edb9f · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.018204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.609953Z digest=sha256:bea425fc0b679184730ec4d0897f724cf36ae34fda72daebb483ba942feac03b

Observation 6fd73aff-c8f0-43c4-a4eb-ac8ac045daa9 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 15

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:39.003234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.623507Z digest=sha256:e759a547d91b17e3665607406de0608eb99fe68dd9c47221beca94c7eb8f7dec

Observation fde42d2b-c679-4b89-b9d4-d136330f7f74 · outbound

This paper cites InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.618708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.618708Z digest=sha256:1bafff49989a55f43f614fdd52cc7af465a8bb2c6fc9cf31a341de8372e8fc9a

Observation f1af8768-1358-4810-8225-43936f42a85a · outbound

This paper cites KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference

Reference 17

Resolution
verified exact
local_arxiv, observed 2026-08-12T00:32:38.527345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.632695Z digest=sha256:4c2c7ed6e997184174d0306dbcfd65b117d63fff24fb35b4906ab0142109d022

Observation 90eaca20-1378-4ee7-abee-fe8262d687d2 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.987077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.627988Z digest=sha256:eda16610df74213893361fad0b46e94efa5955b2e424e859b7f6e53574f7e70a

Observation 329c59ab-7894-4f2a-b291-92dac0dd6381 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.969312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.642228Z digest=sha256:d036c96e35e6fdf9239b86bddbdc0a86d638533bd1545f00b8e5bfe903b3f2b2

Observation fa98d9e0-05c9-4048-8494-33111dac299e · outbound

This paper cites Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale

Reference 20

Resolution
verified exact
local_arxiv, observed 2026-08-12T00:32:38.505931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.637449Z digest=sha256:294b4a1f9de27c5c8967e4b4f3a1cd844023f9d136d4ab82be830d7992d423e9

Observation bb8e88f1-9d60-4275-92e9-ebbfc6a509e8 · outbound

This paper cites AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-08-12T00:32:38.393837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.651350Z digest=sha256:a2912723c42b9d2f4e6acef8127d95f54ee664fa8ca11571df4d31ec59e83052

Observation 7340ac47-0189-4b09-a9d8-188fa296265c · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.646859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.646859Z digest=sha256:649c6e52070cc66f3f235add97449fe22ed69921e695aab75e7f4ed2c0021e96

Observation 76cc6429-15e8-406e-8cb8-5edf2bfcd724 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.935417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.659855Z digest=sha256:a07684ff5c5d9050a50380d3d867c29125bc9d933b5471f0654c234a14032e9c

Observation 956f4cbe-a696-466f-a363-0827e0387c53 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.951813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.655699Z digest=sha256:a35df9f000753b92a8168c5e0a8760379f161974f0962591b4eb11d7b57264d0

Observation 550cb5d8-15a7-4894-93e3-f5624139423c · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.920419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.668311Z digest=sha256:9260cf7247775073c3ce6b74474126a8a518f1614c64d666665ed215a33dcd7b

Observation f3a94a7a-f955-4c64-88b8-71a87606046b · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.663878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.663878Z digest=sha256:85f5637ee001713b6fca21f13b130f644c2b694e391e52cd533a2ed9d2e2de2d

Observation 29f2e448-e553-43b8-b173-3b20bc724e73 · outbound

This paper cites Qwen3 Technical Report.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Qwen3 Technical Report

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.676424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.676424Z digest=sha256:2268f399ee8c20e1146ad9cf8cb0e54c480bec647f1f9e24f9a36fbc63c87f44

Observation e808feac-a137-4a0d-961a-ef5d0a3a755c · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.906117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.672425Z digest=sha256:516d24174e0be9b6377fa037154f54828e57de64293b7f296bed25d861e44a32

Observation 34de9866-6f3f-4ba6-ba4e-a08d451285af · outbound

This paper cites Graham Lopez, Matthew B.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Graham Lopez, Matthew B

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.685118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.685118Z digest=sha256:16acca4ce261f485250690e1e9cbbfbfdc654f534446d665b10d074e3934ab62

Observation 1972923b-11ba-4575-9ffe-b25ed95ee239 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.891328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.681078Z digest=sha256:7f123f3022b2b52b5c1b841686b30e7cbbb24ef8690e13f042e35fcfc7bf7a86

Observation 18f2639a-c252-41ff-bc85-258af43f0643 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.694091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.694091Z digest=sha256:8e7a051eecff134f644361663cc190e7b261cad9ff2d42c6126a8f813cb7ccfe

Observation 3a033333-3dc6-44ff-94f6-e1e6a600920c · outbound

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

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.689283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.689283Z digest=sha256:08341ea7ad26a615156fce8bed4489c67800dcaa3fdb2c5fc1d5f34efb5c1559

Observation 1735977b-82d3-4f0f-b7b3-151147e1617f · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.850226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.703202Z digest=sha256:de6dc6d749def121fcbbead67fdcdbad63195d516a3de78ba2c2d3ccc3e21310

Observation 52ae3910-5989-4d31-9cbd-42caa94de572 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-12T00:32:38.865753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.698629Z digest=sha256:28658ddbeadd1d0aecd959bf038d8c9bce7d043895b65cdc9fb094fd4dd67c4a

Observation 84ba5465-a7bf-442f-aa8c-3bb71bcb65a2 · outbound

This paper cites Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.711516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.711516Z digest=sha256:ce49f405d93088b203a9766a7727a628a331887eb9f1263b126658e8f7b94eaa

Observation 5b25bf9d-d2b2-443f-a215-5b1f0bcb48f7 · outbound

This paper cites FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Reference 36

Resolution
verified exact
local_arxiv, observed 2026-08-12T00:32:38.249021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.707312Z digest=sha256:c0e21493a8d931369af7e13fe97edcd26fe1817458214165dbcf0126d0fc1210

Observation a7f522f9-59a4-488e-9dd9-1c179cdfe35f · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Efficient Streaming Language Models with Attention Sinks

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.720042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.720042Z digest=sha256:74349f8ee10ad956a6d27f96b0d81b14e96da11bce90a52f0ac2345105cc535e

Observation 9424f8df-2c5d-4652-9a75-be74b4a95630 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.715845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.715845Z digest=sha256:cca4bc6edffd42dadf95b52ceb5381994d328a3dad99ac6e7fe652ba29b6e83c

Observation 821ccd77-a208-41b5-8e0d-a3dea65effac · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.729048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.729048Z digest=sha256:87140ab52a7a9b5d2a5c427b19e3ec3dcb583eba7f3f5b218987fe04e5330866

Observation fda8b57d-e692-49fc-bc62-15f0d07d7de8 · outbound

This paper cites OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.724381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.724381Z digest=sha256:1c2125e9457a42c3dd3f26b59ecd82f1edcdb9ee331327f6ba0c78fc978f5686

Observation a5edb732-acd9-4849-a066-44e9b495d50b · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 41

Resolution
verified exact
raw_fallback, observed 2026-08-12T00:32:38.001102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.744673Z digest=sha256:c499eb7ba30fb3bf5c69493009f42b4212059c0e704f3213fae6fd61c62fc64f

Observation 398d303e-d41c-4071-8155-f5b2a672ed24 · outbound

This paper cites Can Xiao, Sukmin Cho, Junbong We, Zhixiong Niu, Jianyi Cheng, Yiren Zhao, Youngjin Kwon, Yongqiang Xiong, Rui Ma, and Junyi Liu.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Can Xiao, Sukmin Cho, Junbong We, Zhixiong Niu, Jianyi Cheng, Yiren Zhao, Youngjin Kwon, Yongqiang Xiong, Rui Ma, and Junyi Liu

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:32:38.834752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.733811Z digest=sha256:4cc24b73595c76fe5ecf3ea80074e311bd6ff9280c2256746a0b92ecfbe63b45

Observation ea420bec-81ba-4fef-8e2f-2b0d3f8aaf0c · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 43

Resolution
metadata mismatch
raw_fallback, observed 2026-08-12T00:32:37.900572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.754805Z digest=sha256:cc7b9288124c5b32eb0c3cbe51eca04ac6645251199d4e6023a60a437ee36289

Observation c59c5c3a-4062-4d2f-900e-fd9265d8d609 · outbound

This paper cites Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.759572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.759572Z digest=sha256:79dd5fb4e111d4a74a44c6dd551bbc5c4b877ce9c8c5f7bafa0de63147dc9f49

Observation 83ef0856-0ebf-466a-9b1d-29f6f273156f · outbound

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

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.749739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.749739Z digest=sha256:07c3fe2fab6d095842cd6e0234d01c603618f86d8a8b7bd692fc8ecf273f361b

Observation 214eeae0-b4f1-48b2-b965-3bdfb1f762c2 · outbound

This paper cites an unresolved cited work.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-12T00:32:37.769236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:32:37.769236Z digest=sha256:b47b952ffeb9c3608256971770b3ec43df6ff6f7152ec02c182b2ea1b06aa656

Observation ea346f1f-94eb-4812-a2b2-f75700aec759 · outbound

This paper cites 2026.HiSparse: Turbocharging Sparse Attention with Hierarchical Memory.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching 2026.HiSparse: Turbocharging Sparse Attention with Hierarchical Memory

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:32:38.804338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.764484Z digest=sha256:3438c0b96cd4f9ccdd7e561aea591e2ab51261a2c7b8a84831a01b8f5b3b034d

Observation fed2ad1a-cd36-457a-af62-634b0ac2cb8b · outbound

This paper cites InAdvances in Neural Information Processing Systems, Vol.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching InAdvances in Neural Information Processing Systems, Vol

Reference 2025

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T00:32:38.819315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.739218Z digest=sha256:99a49157dc0d664cd6b677b8d8b23db5051c25a21f52130a6edb7cef36494da6

Observation 1f666ac2-23c8-493e-95a0-a9848418dffe · outbound

This paper cites SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference.

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

Reference 2026

Resolution
metadata mismatch
local_arxiv, observed 2026-08-12T00:32:38.640375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T00:32:37.583190Z digest=sha256:8ef6a2dea7ce44e4fc9f63e5be1c52f8ee42fd30a9a63a43f770c684e153e2bf

Pith citing papers

No inbound Pith citation observations are available.