Pith. sign in

Paper Citation Record · LEDGER

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference

As of 22 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2607.27187.

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

pith.paper-citation-record.v1
2607.27187 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T11:12:06.872499Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

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

measured 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

51 of 51 outbound references displayed

  • verified exact5
  • verified fuzzy0
  • unresolved46
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cff45db8-3909-4071-9181-1b10eb55777d · outbound

This paper cites Claude model family,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Claude model family,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:02.941086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:02.941086Z digest=sha256:3978c46151dcb358a295ecb5974ed7c2337de85b1b0b0c5d6469fa4d0cdff168

Observation 103dda4b-67ae-43ff-8efd-9a6ece7ee0fe · outbound

This paper cites Gemma 3 Technical Report.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Gemma 3 Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.036232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.036232Z digest=sha256:7c897889c23353e5bdcb052f7e3afc8ef486ec7296a1052b9bd48a0297f584a8

Observation 875ff9d6-8966-47cd-9d45-00700bae348c · outbound

This paper cites GPT-5.4,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference GPT-5.4,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.115461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.115461Z digest=sha256:bdf26aca76dfb9d020b682e5235e4d28dbe565ead8a2751efb55adcc7b004ac3

Observation 6098101c-36c4-453b-a213-71ee37af7864 · outbound

This paper cites LLaMA 4 model family,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference LLaMA 4 model family,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.206696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.206696Z digest=sha256:1cd92eeb52e07486ca9a4bb6ac309f1deccca6ca8a13f9dc772f63bb5f223231

Observation 3877b7b6-3e0c-4310-b2dc-aa5b8fa57908 · outbound

This paper cites How to reduce KV cache bottlenecks with NVIDIA Dynamo,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference How to reduce KV cache bottlenecks with NVIDIA Dynamo,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.305827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.305827Z digest=sha256:0bcfb52aa1ee83adae1cda792007cdd6c40cbb326d1b04b4b8bc8787dd2bd83f

Observation d309e6ac-107e-4b42-93c6-6a92b7ce5c69 · outbound

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

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Efficient memory management for large language model serving with PagedAttention,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.395749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.395749Z digest=sha256:ff19fd306fb0b305b04879234ef9e42feaaaa1291a205333014713f5c466a924

Observation 5e1e241b-c291-4009-b143-6473a7cc66c8 · outbound

This paper cites LMCache: An efficient KV cache layer for enterprise-scale LLM inference,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference LMCache: An efficient KV cache layer for enterprise-scale LLM inference,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.472497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.472497Z digest=sha256:3c1b9a4ed6cfafe5d69355ea33a657e5fb6a1335a7ddcd73cb951c225a6ebcf5

Observation 1570ca12-8008-4553-935a-2c53867ff259 · outbound

This paper cites SGLang HiCache: Fast hierarchical KV caching with storage backends,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference SGLang HiCache: Fast hierarchical KV caching with storage backends,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.546371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.546371Z digest=sha256:79332cc303000c18cea3eae3372861c0b1e9c18f1ea5e139a82e899bd576cc70

Observation fcd15579-efd5-4cd7-8a18-66b3093a5520 · outbound

This paper cites DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.599528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.599528Z digest=sha256:a45889e217c032b427d7914595a104d1d177000115012feaa0a55e145d561c37

Observation 162d66e2-e2ff-451e-8edb-0a410a8c30af · outbound

This paper cites Splitwise: Efficient generative LLM inference using phase splitting,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Splitwise: Efficient generative LLM inference using phase splitting,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.707272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.707272Z digest=sha256:ef292438f9d86a17692512b1fdc2567f1c78c7c4036a47cd3b16a77c24e0aa17

Observation 787c1f27-905e-4136-a55d-123351b4d0bc · outbound

This paper cites Mooncake: Trading more storage for less computation—a KVCache-centric architecture for serving LLM chatbot,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Mooncake: Trading more storage for less computation—a KVCache-centric architecture for serving LLM chatbot,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.771388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.771388Z digest=sha256:05b7d4b10a4ef74de9b016e0e30d32148fb85487bcfdc8bf5fa64c259f24ae8c

Observation 79834a84-4c0a-4f10-b7d6-6711560ddb29 · outbound

This paper cites GPUDirect RDMA documentation.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference GPUDirect RDMA documentation

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.883320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.883320Z digest=sha256:f251d9764fdb92ddb5daedb1d51831efd2e69e2eebd01078bd7c4aaff3a68e18

Observation 83033233-0801-48e5-bc1c-8ff764b5570c · outbound

This paper cites NIXL: NVIDIA Inference Transfer Library,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference NIXL: NVIDIA Inference Transfer Library,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:03.943571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:03.943571Z digest=sha256:4c25de0370a30383890f9555cca1b1fc7409e1f3710aa12074bb102af92dba07

Observation f6f0b223-2081-4d5e-b450-2868a92a176c · outbound

This paper cites Compute Express Link Specification 3.1,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Compute Express Link Specification 3.1,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.034607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.034607Z digest=sha256:60b8ddac9a8d8d8ed0861a528eaefba04ccc3826ac0557bc735eb4c40faca074

Observation bc69d663-0550-4ccf-9186-82410ac1a809 · outbound

This paper cites TraCT: Disaggregated LLM serving with CXL shared memory KV cache at rack-scale,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference TraCT: Disaggregated LLM serving with CXL shared memory KV cache at rack-scale,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.109574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.109574Z digest=sha256:fbaa49d8e23caee08b7170cc38e8a561b4e603fddf16ab8d1dbbb0a3a8560c4b

Observation 051a976a-2c5e-440d-8db9-02be13e787e8 · outbound

This paper cites Beluga: A CXL-based memory architecture for scalable and efficient LLM KVCache management,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Beluga: A CXL-based memory architecture for scalable and efficient LLM KVCache management,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.267894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.267894Z digest=sha256:b5673193223ba7bf150d0e82b7c798d4ec0a623780c1c72749cb693ebedfe711

Observation d0d904ce-3c89-4592-850a-fd2509e1861f · outbound

This paper cites A 56-Gb/s hybrid silicon photonic and 5-nm CMOS 3-D-integrated transceiver for optical compute I/O,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference A 56-Gb/s hybrid silicon photonic and 5-nm CMOS 3-D-integrated transceiver for optical compute I/O,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.396129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.396129Z digest=sha256:e0d097ff4581426eeaef37d23d22e6514c13e1a125b832e4ec4abf74cb2f307a

Observation b5d0951a-8b1b-4a40-a8fa-aeb6b2977828 · outbound

This paper cites Photonic Fabric for memory and compute disaggregation,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Photonic Fabric for memory and compute disaggregation,

Reference 18

Resolution
verified exact
doi, observed 2026-07-30T11:16:10.814745Z

Source-reported events for the cited work

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

source=pdf_text observed=2026-07-30T11:12:04.461375Z digest=sha256:98a9463768a023de9c2ca8e3694c1eb6623258be33fa51a2ebd7a3b9ad3c5e83

Observation 1798de0f-2e70-41c8-aec2-622eff302be3 · outbound

This paper cites Benchmarking GPUDirect RDMA on modern server platforms,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Benchmarking GPUDirect RDMA on modern server platforms,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.547242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.547242Z digest=sha256:3d0433e87c4c6fe5d6d1a21b424b2532ad82091e6ee197a05ac5c2c8de22065c

Observation 21b44858-7fc5-4757-976e-711f401e7bf4 · outbound

This paper cites Distributed KV cache scheduling and offloading,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Distributed KV cache scheduling and offloading,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.609485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.609485Z digest=sha256:c9faf7ca1662ee89c8b99863373a22937f00099db52979fdf14fc6822c9d9075

Observation e9ccd45a-f17f-493d-b251-dee6ecfa0f2b · outbound

This paper cites Photonic Fabric: Co-packaged photonic interconnect technology,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Photonic Fabric: Co-packaged photonic interconnect technology,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.692564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.692564Z digest=sha256:758754a741877b7c5385d0b7fbd713e85e00bb1dd79da1ddf0b9b67257e4c95a

Observation 84822ca0-faf7-4dac-bd07-b79bd4870729 · outbound

This paper cites CXL Type 3 Memory Device Software Guide,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference CXL Type 3 Memory Device Software Guide,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.742646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.742646Z digest=sha256:a5967f7b9750950f6203fededbe7a83a7b0c846c32aa64efd3ef26e1ca41b9b3

Observation dbf36d59-84ce-4e4f-a6e2-00fcb52ca369 · outbound

This paper cites KV Connector API.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference KV Connector API

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.832537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.832537Z digest=sha256:bfa3710520617aa90dae46d6757d755b5080b91547540df84df09ed9b0382b8c

Observation 1fad6f1a-2233-4638-ac31-f2f9b7eaf8b9 · outbound

This paper cites Inside vLLM's new KV offloading connector,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Inside vLLM's new KV offloading connector,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:04.885472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:04.885472Z digest=sha256:0c91583e96a4a04a37e10b0b6057bc4671b49d38c4251762cef9d170992b336d

Observation 5ead0c58-9319-4e47-b2a5-f794dc6121d5 · outbound

This paper cites CXL-attached memory allocation for long-context LLM fine-tuning,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference CXL-attached memory allocation for long-context LLM fine-tuning,

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-07-30T11:16:10.524026Z

Source-reported events for the cited work

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

source=pdf_text observed=2026-07-30T11:12:04.969824Z digest=sha256:6b27a2f1615e0c8791abc68fd5fa4f376f95a4e258db407194f3a704e79d4315

Observation abf44001-a060-4cec-9f6a-2ee721c0179d · outbound

This paper cites Intra-device heterogeneous memory allocation support,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Intra-device heterogeneous memory allocation support,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.084954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.084954Z digest=sha256:a158539d8a86adc5210c5f9321caa1ef163ffec432227f8ffd5b274d5e00b5ca

Observation dc0601a6-cce7-40fd-9b57-f0d366b1c406 · outbound

This paper cites LLMServingSim: A runtime-driven HW/SW co-simulation framework for LLM inference serving,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference LLMServingSim: A runtime-driven HW/SW co-simulation framework for LLM inference serving,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.178621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.178621Z digest=sha256:6c4d970a8dfae7a875ca3d331e653bb4f12cd2b4eb5e0516db28581c8d1d1385

Observation 4b9fb5a5-4688-4fc6-b260-e8286dbfead9 · outbound

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

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference SGLang: Efficient Execution of Structured Language Model Programs

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.241515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.241515Z digest=sha256:c484aa1ed0184c2000d05bb8ab7898944356058acc13a83b1c5488577d765127

Observation 11f3bdba-732b-46c5-a783-a8da8dbd4754 · outbound

This paper cites CacheBlend: Fast large language model serving for RAG with cached knowledge fusion,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference CacheBlend: Fast large language model serving for RAG with cached knowledge fusion,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.312542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.312542Z digest=sha256:8fed0029c22355f45ba87e69f54cb144ebccf8f71fb4b92721347f38aa010d0b

Observation 9cedfed7-c3d1-4e05-907b-6e63eabd2a7f · outbound

This paper cites Pond: CXL-based memory pooling systems for cloud platforms,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Pond: CXL-based memory pooling systems for cloud platforms,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.370656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.370656Z digest=sha256:f2daf5832f6c4b64ce183b7c6e553090ba88b6a3e46fad957e0b7bccd0870d0c

Observation 7a34ede7-3f6b-4938-b5a4-fcc82dba9cf0 · outbound

This paper cites InfiniGen: Efficient generative inference of large language models with dynamic KV cache management,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference InfiniGen: Efficient generative inference of large language models with dynamic KV cache management,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.426496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.426496Z digest=sha256:e26da22e88533cb54e0df1cc32572b3162b134870ac54dca82e9e4eb17b8fbd0

Observation 332bdf53-8995-4706-ac1f-6ac7695eadcf · outbound

This paper cites KVQuant: Towards 10 million context length LLM inference with KV cache quantization,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference KVQuant: Towards 10 million context length LLM inference with KV cache quantization,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.536329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.536329Z digest=sha256:b4cb6197e4b498556c3794c43485fbae8cdc280f990d4a6673aba979611df01d

Observation 884912ea-535c-4233-8ae2-fc767a427533 · outbound

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

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.690037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.690037Z digest=sha256:581d7a87ad47de2169c099f9fd276205496ba8237dc2bbc3b0300e2be5a1812e

Observation 270ca459-9ac7-4564-81ca-0a1b40cfb920 · outbound

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

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.608333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.608333Z digest=sha256:ea0f9c2e6d7a7c06ef840f7d35f6ebecdfb7e979d532bd2009ff97c2025e37df

Observation 7237382f-43e1-4957-b1e0-10fe1e064b54 · outbound

This paper cites DirectCXL: Direct memory access for CXL-enabled memory disaggregation,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference DirectCXL: Direct memory access for CXL-enabled memory disaggregation,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.883851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.883851Z digest=sha256:940aec091300c4c06a523705a7873ea28490d0bd0ed35618044856c0a618fda2

Observation 5dd9a917-eda8-4d57-a53a-8b43078d961c · outbound

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

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.779480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.779480Z digest=sha256:139ae99ce7337fdf134ac54dcf242b5ac0f0e1bd6ea715c49b6d6417fc225e1a

Observation c4a6862e-59b5-4046-9637-30f917d0bcfc · outbound

This paper cites Melody: Systematic CXL memory characterization and performance analysis at scale,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Melody: Systematic CXL memory characterization and performance analysis at scale,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.067388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.067388Z digest=sha256:60007fb97edcddc42bc687c11354805882957cfa043f0bffa3a8174cd68b2545

Observation c1d62af3-1e6e-432e-8768-a51a4b7a7c60 · outbound

This paper cites TPP: Transparent page placement for CXL-enabled tiered memory,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference TPP: Transparent page placement for CXL-enabled tiered memory,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.953149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.953149Z digest=sha256:1d60e08e4d9b869c404c6ea8d9c9eec35c6f47f7e66fcb8a978f5b61e8b8a4d7

Observation b058653b-c660-462f-8d8a-20244d267ee3 · outbound

This paper cites RCMP: Reconstructing RDMA-based memory disaggregation via CXL,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference RCMP: Reconstructing RDMA-based memory disaggregation via CXL,

Reference 39

Resolution
verified exact
doi, observed 2026-07-30T11:16:10.065070Z

Source-reported events for the cited work

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

source=pdf_text observed=2026-07-30T11:12:06.255890Z digest=sha256:b505d5d6c0dc310375b04edcbc1da98c41e436c677fbe21c79663d4577e459b3

Observation 1110d836-1c6d-4dd4-befc-b1d1a43b3d87 · outbound

This paper cites Hilfer fractional advection-diffusion equations with power-law initial condition; a Numerical study using variational iteration method.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Hilfer fractional advection-diffusion equations with power-law initial condition; a Numerical study using variational iteration method

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.165612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.165612Z digest=sha256:61edca12d300a5fa5d109708090514c6510134c17817043052c2fc00364922c1

Observation 623b1fc4-5f11-4c9e-a694-bc782cd80b1c · outbound

This paper cites Tomahawk 6 (Davisson) co-packaged optics switch,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Tomahawk 6 (Davisson) co-packaged optics switch,

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.416077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.416077Z digest=sha256:5c379545d9118e6da6f4f3b1018e04d8a7f9f7fda734eddb33099ff403b8d2ac

Observation 225ab3d1-5644-4b89-b720-6e49349a991f · outbound

This paper cites Scaling out data parallel applications with CXL-Ethernet hybrid interconnects,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Scaling out data parallel applications with CXL-Ethernet hybrid interconnects,

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-07-30T11:16:09.888961Z

Source-reported events for the cited work

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

source=pdf_text observed=2026-07-30T11:12:06.353034Z digest=sha256:279721ce5bd5ca66ef855435bcfa1fd57d9e6c8b4625423312062a25423ec367

Observation 09f2a26a-8efe-4285-ae8e-13dd24398461 · outbound

This paper cites Monolithic electro-optic platform on silicon with bandwidth of 100 GHz and beyond,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Monolithic electro-optic platform on silicon with bandwidth of 100 GHz and beyond,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.586635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.586635Z digest=sha256:a1d092776f1ea39a662dd2d71e931c8748d8a4e07a1ea05105109157081f973d

Observation 33792e26-22f7-431f-bcfd-04c7f57e660b · outbound

This paper cites Optical Compute Interconnect (OCI),.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Optical Compute Interconnect (OCI),

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.471577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.471577Z digest=sha256:d14198f2a82aa21de65d7e1ca670e4cfafca1c68ae6dc94da8538db905e5ab1a

Observation df41c7c0-e4a6-4aef-892f-0e97a893211c · outbound

This paper cites Available: https://www.intel.com/content/www/us/en/research/optical-compute- interconnect.html.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Available: https://www.intel.com/content/www/us/en/research/optical-compute- interconnect.html

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.522337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.522337Z digest=sha256:36c9616bf7c72507cbd333c2f46ae52f8c06a6db65a14426bd4484f2bc99e5f7

Observation d7e5fbcc-e80b-45b7-b84e-b303efc89fd3 · outbound

This paper cites TeraPHY: 3rd generation UCIe optical chiplet,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference TeraPHY: 3rd generation UCIe optical chiplet,

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.837560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.837560Z digest=sha256:f303930a85f588c030fc7d2fee67a1b48ad9bb3960360395659efd461c7b8470

Observation b399f4f8-dff3-4c69-a259-0b9d66549c8a · outbound

This paper cites A new era in data center networking with NVIDIA silicon photonics-based network switching,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference A new era in data center networking with NVIDIA silicon photonics-based network switching,

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.872499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.872499Z digest=sha256:05d32c36e3429158f6db04fecace0eeb3e707ec09fcd631d6da6c2d28a2f4754

Observation 0089088e-0d1e-4251-925d-0d7a836da0ca · outbound

This paper cites Beyond-110 GHz C-band GeSi electro-absorption modulator on 300 mm silicon photonics,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Beyond-110 GHz C-band GeSi electro-absorption modulator on 300 mm silicon photonics,

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.699764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.699764Z digest=sha256:5adda7754c5c219d772aee056ed348545a5cf55fa491b22e4f2b0454e451f8fd

Observation 3b230690-70c7-4271-930c-3e4ba49d3169 · outbound

This paper cites Passage M1000 photonic superchip,.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Passage M1000 photonic superchip,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:06.785535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:06.785535Z digest=sha256:e92d639b50952ffc0037eaf523000c827216be1aed2c0eb79270588a41f9b9aa

Observation 1a3740c8-c49c-4095-8e1c-a6812b2aae33 · outbound

This paper cites Available: https://www.usenix.org/conference/osdi24/presentation/lee.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Available: https://www.usenix.org/conference/osdi24/presentation/lee

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-07-30T11:12:05.474858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-30T11:12:05.474858Z digest=sha256:28d4b8d47841e902cb2ba2376b2ec18e3eb6dc85ffdb38808f88fd9720843b2f

Observation ea7d9c25-0041-4474-acf2-2b9ab481e7c6 · outbound

This paper cites an unresolved cited work.

A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference Unresolved cited work

Reference 2025

Resolution
verified exact
doi, observed 2026-07-30T11:16:09.697183Z

Source-reported events for the cited work

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

source=pdf_text observed=2026-07-30T11:12:06.638543Z digest=sha256:5f3cd746bbfdf04f8eef2b9e3f01386f892f08d8b91bede69748f0c72ac39247

Pith citing papers

No inbound Pith citation observations are available.