Paper Citation Record · LEDGER

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference

As of 23 July 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2604.26557.

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

pith.paper-citation-record.v1
2604.26557 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-07T12:51:42.916410Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-23T06:31:01.910684+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

47 of 47 outbound references displayed

verified exact9
verified fuzzy37
unresolved0
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 970792c5-a738-409a-9064-a5ae51dc645e · outbound

This paper cites A review on edge large language models: Design, execution, and applications.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference A review on edge large language models: Design, execution, and applications

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.794640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c965984f-a1ad-4e57-a157-162a1cb06049 · outbound

This paper cites A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial llm services.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial llm services

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:06:26.539616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a1a76803-32f5-49ac-80d3-f628cebb426b · outbound

This paper cites Mobilellm: Optimizing sub- billion parameter language models for on-device use cases.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Mobilellm: Optimizing sub- billion parameter language models for on-device use cases

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.807121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 4062ded4-711d-4bce-9eec-330733d03515 · outbound

This paper cites Intelligent data analysis in edge com- puting with large language models: applications, challenges, and future directions.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Intelligent data analysis in edge com- puting with large language models: applications, challenges, and future directions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.849755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8e0d5816-a7a6-4150-a1b8-fdf121bbd6b7 · outbound

This paper cites CUDA Programming Guide: Unified and system mem- ory.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference CUDA Programming Guide: Unified and system mem- ory

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.812880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e291abe5-5b35-4b7e-8632-c55e2bccfee0 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Gemma: Open Models Based on Gemini Research and Technology

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-12T09:06:26.510120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 07c1500e-e8c4-43e7-9dd3-c1f0bafc4a74 · outbound

This paper cites Mistral 7B.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Mistral 7B

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-12T09:06:26.529461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 533b9f04-6e59-4be0-ad72-2d35bf5d5362 · outbound

This paper cites The Llama 3 Herd of Models.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference The Llama 3 Herd of Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-12T09:06:26.534152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c5bdda9d-dcf2-4b01-987c-f77ddc87440a · outbound

This paper cites Longreward: Improving long-context large language models with ai feedback.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Longreward: Improving long-context large language models with ai feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.789106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation d3203377-fd91-4f8f-a5c5-e1cf4399bf01 · outbound

This paper cites Longbench: A bilingual, multitask benchmark for long context understanding.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Longbench: A bilingual, multitask benchmark for long context understanding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.791735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 2eaf2ecb-bfb9-4d1a-8d40-a4c5fdc1d73f · outbound

This paper cites Visual instruction tuning.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Visual instruction tuning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.797731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6c880d7d-283e-4f27-b180-0826a8a0e2a2 · outbound

This paper cites Logparser-llm: Advancing efficient log parsing with large language models.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Logparser-llm: Advancing efficient log parsing with large language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.800615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e62b4a2f-4854-40bc-bc4a-af8a0e903e06 · outbound

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

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.786627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 28a86021-209b-497e-9c4f-09325b8bb454 · outbound

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

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Flexgen: High-throughput generative inference of large language models with a single gpu

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.784026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 72fbe47a-cf7f-4b87-b2d7-43e486ba1424 · outbound

This paper cites Attention is all you need.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Attention is all you need

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.844599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e0c86885-4aa6-4a0a-b7e9-a5f12923d31d · outbound

This paper cites Infinigen: Efficient generative inference of large language models with dynamic kv cache manage- ment.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Infinigen: Efficient generative inference of large language models with dynamic kv cache manage- ment

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.818998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5099a91b-04ec-401b-b1d9-e180df3497e6 · outbound

This paper cites llama.cpp: Llm inference in c/c++.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference llama.cpp: Llm inference in c/c++

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.815558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8a0e41bc-7d9d-4d9f-9699-3baf8cdd2671 · outbound

This paper cites Lmcache: An efficient kv cache layer for enterprise-scale llm inference.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Lmcache: An efficient kv cache layer for enterprise-scale llm inference

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:06:26.545204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b97e96bc-ce18-42c5-a622-a10245d5786b · outbound

This paper cites Powerinfer: Fast large language model serving with a consumer-grade gpu.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Powerinfer: Fast large language model serving with a consumer-grade gpu

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.847092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 43f22c5d-b873-4d8e-ae59-6d1f52e518b7 · outbound

This paper cites KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:06:26.515079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0e4f2afc-c9b7-4b6f-b6fe-f402d2781efe · outbound

This paper cites Llm in a flash: Efficient large language model inference with limited memory.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Llm in a flash: Efficient large language model inference with limited memory

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.841912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 939ef159-377f-4b61-9faa-77c20137241a · outbound

This paper cites Designing a true direct-access file system with devfs.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Designing a true direct-access file system with devfs

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.769716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8bbe7533-8e6a-4322-a812-bb99ce68b502 · outbound

This paper cites Storage performance development kit (spdk).

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Storage performance development kit (spdk)

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.766803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6830ef55-1c88-42db-9a7c-19450044ef1b · outbound

This paper cites an unresolved cited work.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Unresolved cited work

Reference 24

Resolution: parse uncertain; raw_fallback, observed 2026-05-27T06:18:52.775565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 44b10cd0-9821-4a0d-9bff-1934176621b8 · outbound

This paper cites Flashshare: Punching through server storage stack from kernel to firmware for ultra-low latency ssds.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Flashshare: Punching through server storage stack from kernel to firmware for ultra-low latency ssds

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.760390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 73d94845-dcd5-4f2f-8090-c32daabd4c3c · outbound

This paper cites I/o passthru: Upstreaming a flexible and efficient i/o path in linux.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference I/o passthru: Upstreaming a flexible and efficient i/o path in linux

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.754131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 4efa9446-4204-4693-bcaa-bc9ec6c7fbf6 · outbound

This paper cites Opt-6.7b.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Opt-6.7b

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.748372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 996224ef-2f4d-4422-befd-89d09c9d80fa · outbound

This paper cites X3: A low overhead high performance buffer management replacement algorithm.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference X3: A low overhead high performance buffer management replacement algorithm

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.772838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 9136f0ee-5ef5-433e-8a51-12a2cfc4c3a5 · outbound

This paper cites Arc: A self-tuning, low overhead replacement cache.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Arc: A self-tuning, low overhead replacement cache

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.745700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 823641a5-b407-4aa0-9775-2d93fa1dc916 · outbound

This paper cites Streamcache: Revisiting page cache for file scanning on fast storage devices.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Streamcache: Revisiting page cache for file scanning on fast storage devices

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.751246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 1101bdff-c005-4abb-841a-2785741d0ed2 · outbound

This paper cites Gregg,BPF performance tools.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Gregg,BPF performance tools

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.756947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 92217bb7-fffe-47ce-af08-9b78c936aa74 · outbound

This paper cites Asynchronous i/o stack: A low-latency kernel i/o stack for ultra-low latency ssds.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Asynchronous i/o stack: A low-latency kernel i/o stack for ultra-low latency ssds

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.763199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b456fee8-6ce8-41f0-9697-ccb835151936 · outbound

This paper cites D2FQ:Device-Direct Fair Queueing for NVMe SSDs.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference D2FQ:Device-Direct Fair Queueing for NVMe SSDs

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.778401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8de83568-eb69-4f4b-ab94-ba1fef7131f5 · outbound

This paper cites iJournaling:Fine-Grained journaling for improving the latency of fsync system call.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference iJournaling:Fine-Grained journaling for improving the latency of fsync system call

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.828454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b9e57702-adab-4729-9b91-61d8886df1c7 · outbound

This paper cites Asynchronous i/o support in linux 2.5.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Asynchronous i/o support in linux 2.5

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.821871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e0838906-55df-4c7f-be66-30944e20dcfa · outbound

This paper cites Do we still need io schedulers for low-latency disks?.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Do we still need io schedulers for low-latency disks?

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.839154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0b22dbcb-5396-4a6e-a86f-7174feff4de9 · outbound

This paper cites Bfq, multiqueue- deadline, or kyber? performance characterization of linux storage sched- ulers in the nvme era.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Bfq, multiqueue- deadline, or kyber? performance characterization of linux storage sched- ulers in the nvme era

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.836740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3b336d32-789a-4534-83fd-984717ec7570 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference OPT: Open Pre-trained Transformer Language Models

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-12T09:06:26.505328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 96561b3a-073a-4357-a418-d001abd9cb8a · outbound

This paper cites Cuda c++ programming guide.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Cuda c++ programming guide

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.831054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 887e8ffd-7f93-45ca-b673-6024568ad8a4 · outbound

This paper cites Can Foundation Models Wrangle Your Data?.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Can Foundation Models Wrangle Your Data?

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:06:26.520020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5147f533-fb3b-4f48-aaf1-d4bb6051c84d · outbound

This paper cites Cost-efficient large language model serving for multi-turn conversations with cachedattention.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Cost-efficient large language model serving for multi-turn conversations with cachedattention

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.781127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 73247e4d-6233-41a7-8fba-e6d1a616e7d6 · outbound

This paper cites An i/o characterizing study of offloading llm models and kv caches to nvme ssd.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference An i/o characterizing study of offloading llm models and kv caches to nvme ssd

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.825230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation d7d8662d-d962-417a-9f9e-fac135a34a56 · outbound

This paper cites InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:06:26.525019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f1eb7498-279d-430f-899d-d14b3403aa0a · outbound

This paper cites INF2: High- throughput generative inference of large language models using near- storage processing.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference INF2: High- throughput generative inference of large language models using near- storage processing

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.803707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 76222427-6bc4-4968-b5bc-9989dc9a59dd · outbound

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

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Efficient memory management for large language model serving with pagedattention

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.810087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 55b4c814-6c56-4d6a-9f28-fee673c70855 · outbound

This paper cites GPUDirect Storage: A Direct Path Between Storage and GPU Memory.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference GPUDirect Storage: A Direct Path Between Storage and GPU Memory

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.852734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 143753e3-c563-4e07-826e-eeef2a96793d · outbound

This paper cites Gpu- initiated on-demand high-throughput storage access in the bam system architecture.

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Gpu- initiated on-demand high-throughput storage access in the bam system architecture

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T06:18:52.833824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Pith citing papers

No inbound Pith citation observations are available.