Pith. sign in

Paper Citation Record · LEDGER

Mixture-of-Experts Serving

As of 16 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 1 inbound Pith citation observation for arXiv:2607.17880.

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

pith.paper-citation-record.v1
2607.17880 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:48:23.938414Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:51:05.684119Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T17:51:06.516646Z

Reference resolution

48 of 48 outbound references displayed

  • verified exact1
  • verified fuzzy34
  • unresolved13
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4da8c282-ed38-402b-b9f9-6c8245885a0e · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Mixture-of-Experts Serving gpt-oss-120b & gpt-oss-20b Model Card

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.416951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.416951Z digest=sha256:21e17973720c0f1a13e2f8ac21a7006766e0a123c04a33a09bceb9b1eb98d89f

Observation 9e1e8c54-9aee-40d6-9ab2-bbd39ef51aa8 · outbound

This paper cites Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve.

Mixture-of-Experts Serving Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.770905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.421639Z digest=sha256:c92230870bd43be1ce316db3b7f165cafa233b118beb1c77f2df7aa70f24df7b

Observation 786cea2b-c888-4a5f-88e1-b1008924ba46 · outbound

This paper cites A tale of two metrics: Simultaneous bounds on competitiveness and regret.

Mixture-of-Experts Serving A tale of two metrics: Simultaneous bounds on competitiveness and regret

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.673869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.425367Z digest=sha256:825613d52578ef6a178256da593041eaf6ef89717a02004f18c02cd26116cd74

Observation ea427b73-279b-4452-8a90-afc5da6b36c2 · outbound

This paper cites Dimension-free bounds for chasing convex functions.

Mixture-of-Experts Serving Dimension-free bounds for chasing convex functions

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.429693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.429693Z digest=sha256:a92061b7bca88dd429c848979895c6d27de5357333342dcf6778b7525b8557ef

Observation a38ad19f-8b7b-4b3a-b1f8-a1aed33f17d2 · outbound

This paper cites Online algo- rithms for covering and packing problems with convex objectives.

Mixture-of-Experts Serving Online algo- rithms for covering and packing problems with convex objectives

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.563896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.434405Z digest=sha256:22b59037301abb4a119b0683a73bbd218c3e5a2a0d33b880f5f380321b1a552c

Observation fd4d32d6-8a3b-4493-9df1-e9d56022e293 · outbound

This paper cites Randomized competitive algorithms for generalized caching.SIAM Journal on Computing, 41(2):391–414, 2012.

Mixture-of-Experts Serving Randomized competitive algorithms for generalized caching.SIAM Journal on Computing, 41(2):391–414, 2012

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.550321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.438688Z digest=sha256:4ba34afce7c1d6bb32447aa5d5e810946ed6625418462c90cf3205fa19a1955f

Observation ca1b3255-af10-4425-8bc7-6e155426eb0f · outbound

This paper cites A 2-competitive algorithm for online convex optimization with switching costs.

Mixture-of-Experts Serving A 2-competitive algorithm for online convex optimization with switching costs

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.538932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.443092Z digest=sha256:0af911d7e01e283221b9fe5c0abb09504d9b409399869da5e5ab99691d1fdbc8

Observation 72c45e28-3f7d-4cea-95fa-151ebb330bb2 · outbound

This paper cites A polylog (n)-competitive algo- rithm for metrical task systems.

Mixture-of-Experts Serving A polylog (n)-competitive algo- rithm for metrical task systems

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.527119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.447373Z digest=sha256:499d88ffc43c69273c451dbe15d9c8b33b540c75c3e2ebe06c371b9298f5fcb6

Observation a043f6d3-6976-4f6d-8140-307777254f1b · outbound

This paper cites Nonclairvoyant scheduling to minimize the total flow time on single and parallel machines.Journal of the ACM (JACM), 51(4):517–539, 2004.

Mixture-of-Experts Serving Nonclairvoyant scheduling to minimize the total flow time on single and parallel machines.Journal of the ACM (JACM), 51(4):517–539, 2004

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.443957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.451468Z digest=sha256:cdde65dc9ca2f71eb0c257f4f711242dbd805778c595876f5a4ad1691e535c2a

Observation b2a74e08-b639-4e2a-b12e-173e8e161b31 · outbound

This paper cites Finely-competitive paging.

Mixture-of-Experts Serving Finely-competitive paging

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.293830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.455664Z digest=sha256:7690ca0d78117078c9187bf0a75e2c932087a7fd04526f4fa6b6e4939b629fb3

Observation 74bfd8e3-fc73-467c-83f5-6b712d290abd · outbound

This paper cites An optimal on-line algorithm for metrical task system.Journal of the ACM (JACM), 39(4):745–763, 1992.

Mixture-of-Experts Serving An optimal on-line algorithm for metrical task system.Journal of the ACM (JACM), 39(4):745–763, 1992

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.204368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.459969Z digest=sha256:873cb38b14ebce885a7743cbf3e48ea0e0dd5e5232c9cbc0b374a711e3c856a8

Observation a9e9540a-7ca3-4459-8623-bc13191fdf9f · outbound

This paper cites K- server via multiscale entropic regularization.

Mixture-of-Experts Serving K- server via multiscale entropic regularization

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.118977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.464004Z digest=sha256:8adabd3e7abab5c47440821f1fb67124993fc5d5f08316c8fd944f45854769aa

Observation 25692a8a-85d9-4b85-a210-1ea18089a983 · outbound

This paper cites Competitively chasing convex bodies.

Mixture-of-Experts Serving Competitively chasing convex bodies

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.107316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.468087Z digest=sha256:d652ba5597513da59004b67d4f3508d9883bef1279a748ea1b2843ac9e1e6307

Observation ce2a5491-5f69-4cef-b071-08454d57978e · outbound

This paper cites Competitive analysis via regularization.

Mixture-of-Experts Serving Competitive analysis via regularization

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.095132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.471963Z digest=sha256:84c95823bf6d0653a74d7f08d737679e21b56b340bbdd6b803d3478a17bbe1c7

Observation 7a891bd2-2502-47a6-a7b6-01f8c6652fff · outbound

This paper cites k-servers with a smile: Online algorithms via projections.

Mixture-of-Experts Serving k-servers with a smile: Online algorithms via projections

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.083332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.485996Z digest=sha256:5141d320a85e07715c207f943e6ebd08d752f6a7c6e1646bcd1fb440c3a48798

Observation 655564b3-f37e-4c7d-b271-0b5dbdc3fffd · outbound

This paper cites Minimizing total completion time on batch processing machines.The International Journal Of Production Research, 31(9):2097–2121, 1993.

Mixture-of-Experts Serving Minimizing total completion time on batch processing machines.The International Journal Of Production Research, 31(9):2097–2121, 1993

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.070681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.611298Z digest=sha256:373aa6fa5a88559916fad9b49315c94282d90996a1f1971ab6ddc48e99097d81

Observation a58bbc78-2e6e-48c8-a41d-a896110b4478 · outbound

This paper cites Smoothed online convex optimization in high dimensions via online balanced descent.

Mixture-of-Experts Serving Smoothed online convex optimization in high dimensions via online balanced descent

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.619890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.619890Z digest=sha256:d63af4f22923c416cb595bb7a1b8dae77ec8d36af432aeccb59f6c74e32d17de

Observation 52f5d9b1-bb26-4abf-b22b-4f761b61ed85 · outbound

This paper cites Pure entropic regularization for metrical task systems.

Mixture-of-Experts Serving Pure entropic regularization for metrical task systems

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.045098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.644639Z digest=sha256:b67c4d6b10987a949150eb9a62753cf3d620513444240ed5d099b24eb9e72a8d

Observation def63396-bdd4-4aa8-957b-0a3a6396afb0 · outbound

This paper cites Deepseekmoe: Towards ultimate expert specializa- tion in mixture-of-experts language models.

Mixture-of-Experts Serving Deepseekmoe: Towards ultimate expert specializa- tion in mixture-of-experts language models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.648070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.648070Z digest=sha256:843968ca1753f86c706de1c354d9bbc20786450a6af0194fdd7436885c4e39ec

Observation 4948f036-9cc3-47b2-bf22-9f2f2d45a3de · outbound

This paper cites Primal dual gives almost optimal energy efficient online algorithms.

Mixture-of-Experts Serving Primal dual gives almost optimal energy efficient online algorithms

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.020026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.651998Z digest=sha256:1f962d392abb581cfefbbe57a87b2c533f9f17130f689f3ec70ae96693cc21f2

Observation 3dae5166-e8cd-4de5-952a-ff413deba37c · outbound

This paper cites Online matching with concave returns.

Mixture-of-Experts Serving Online matching with concave returns

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:25.008814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.655303Z digest=sha256:6ed11d1807f7b575bedf723b4e3116d8bbf2382474123c43aecaf59b46d5e5b3

Observation a0c4965a-5e57-4d8a-99f6-0f3ab50f6f36 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022.

Mixture-of-Experts Serving Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.659451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.659451Z digest=sha256:da5b40414c1e6cfd803c77cecdf8bcf616508700119ddca5f65053178540eee6

Observation af525856-accc-4003-8eb7-595d5ce46203 · outbound

This paper cites Competitive paging algorithms.Journal of Algorithms, 12(4):685–699, 1991.

Mixture-of-Experts Serving Competitive paging algorithms.Journal of Algorithms, 12(4):685–699, 1991

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.957872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.663889Z digest=sha256:628aac46ec4527982e6a81c65e0ce47a932b4f53577ead751d306cac03f96cda

Observation 1003127d-8d49-4d2a-ae54-97fefb6baed8 · outbound

This paper cites On convex body chasing.Discrete & Computational Ge- ometry, 9(3):293–321, 1993.

Mixture-of-Experts Serving On convex body chasing.Discrete & Computational Ge- ometry, 9(3):293–321, 1993

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.727799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.668284Z digest=sha256:9d38373d9c10594ee861fe65fcd1091449e34b189662aecbff7e012cbf1a3ef2

Observation 26e15a36-4c77-430c-9d9e-9c576bc2df9c · outbound

This paper cites MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing.

Mixture-of-Experts Serving MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.671881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.671881Z digest=sha256:7db9fe28b10526ec7567acb05cb4398b60238a1c1e890a1fd12851ba429ef4d0

Observation 759d6ed9-748b-4ee2-8f1e-0ec86a4d055b · outbound

This paper cites Gemini 3 Pro model card, November 2025.

Mixture-of-Experts Serving Gemini 3 Pro model card, November 2025

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.687894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.675602Z digest=sha256:144a7085f9e7f3b7ab77471c5f1a7feceabd30981320908d410ca7ca3e898bb9

Observation 336b506f-a1f2-4e56-a2dd-67110a9816b1 · outbound

This paper cites Scheduling semiconductor burn-in operations to minimize total flowtime.Operations research, 45(6):874–885, 1997.

Mixture-of-Experts Serving Scheduling semiconductor burn-in operations to minimize total flowtime.Operations research, 45(6):874–885, 1997

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.669653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.679215Z digest=sha256:9e513756f46c5fda44edbcc61bc6c1d1b1c8f6f99d7f94e7601ea0f6d040a795

Observation 60cc2c7b-b1e2-480b-a56d-c8b2e4c77147 · outbound

This paper cites Welfare maximization with production costs: A primal dual approach.

Mixture-of-Experts Serving Welfare maximization with production costs: A primal dual approach

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.653646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.683328Z digest=sha256:1c7c44034e94e7bef56aa94368b44962ddbd45f14d7b016e7095613ae3e19d01

Observation e1ed8e23-6e10-4601-8e34-b967e6fb34f3 · outbound

This paper cites Adaptive mixtures of local experts.Neural computation, 3(1):79–87, 1991.

Mixture-of-Experts Serving Adaptive mixtures of local experts.Neural computation, 3(1):79–87, 1991

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.687681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.687681Z digest=sha256:3c250b4efac8893cfcbb69215356d9f7d23949a589cde8375f34014dfa5154ad

Observation 4248654f-d24a-4415-90e8-79de1cbe1d87 · outbound

This paper cites Online scheduling for llm inference with kv cache constraints.arXiv preprint arXiv:2502.07115, 2025.

Mixture-of-Experts Serving Online scheduling for llm inference with kv cache constraints.arXiv preprint arXiv:2502.07115, 2025

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.690925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.690925Z digest=sha256:ac53b03ca4351af322d073eaebbc303e53ef8c75c8e298163dbf5fc770040556

Observation cbb4dd47-c88e-4549-bedf-7cae33a5e157 · outbound

This paper cites Mixtral of Experts.

Mixture-of-Experts Serving Mixtral of Experts

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.695836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.695836Z digest=sha256:15a35145e93d6c1bf552d46018e7a75d21ab17bd83a79e98590d4975210e9968

Observation e138f387-f304-4b57-a737-d7dd9aa475ac · outbound

This paper cites Hierarchical mixtures of experts and the em algorithm.

Mixture-of-Experts Serving Hierarchical mixtures of experts and the em algorithm

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.626069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.700992Z digest=sha256:98678c31cc209010c88c14af92aabc9b08315ff3ff791567a4e3220143d83da0

Observation fbe0ae2d-a7a0-4172-8429-307b3a11e12e · outbound

This paper cites Speed is as powerful as clairvoyance.Journal of the ACM (JACM), 47(4):617–643, 2000.

Mixture-of-Experts Serving Speed is as powerful as clairvoyance.Journal of the ACM (JACM), 47(4):617–643, 2000

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.606250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.704836Z digest=sha256:c1a25514bc555b89b6d0bb8e28c64657a01b1cd4b486d39a3605d04daa5a750c

Observation 4127e9a9-0509-4cde-afe4-9b64eda321ac · outbound

This paper cites Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice.

Mixture-of-Experts Serving Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

Reference 34

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:48:24.044715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.730473Z digest=sha256:f7ba15107358931a75a8bfde210cbfbd3c00a5a4642213ad6884077ccfff889a

Observation 9da8f409-90b9-4008-a9a0-5260e94b086f · outbound

This paper cites Papadimitriou.

Mixture-of-Experts Serving Papadimitriou

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.483584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.772280Z digest=sha256:0325961d52bf1eda231495d272d540d21f2c3d12deb82f7d86d3ce6785cec9a6

Observation 0183a152-81d7-4b22-8a12-d006161a25d4 · outbound

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

Mixture-of-Experts Serving Efficient memory management for large language model serving with pagedattention

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.820300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.820300Z digest=sha256:e04a2383a6f405515ddbc89a51d2b2809ebaad8a0a3c2469a7e710b9653a789a

Observation 400d3e83-fdb1-407f-9b9b-d11eb11f9c19 · outbound

This paper cites Accelerating distributed MoE training and inference with lina.

Mixture-of-Experts Serving Accelerating distributed MoE training and inference with lina

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.389210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.860657Z digest=sha256:1b8c29ecf51d3c54e3fb80816a267352cce27d77e678e42ab624f431a4fec369

Observation 4ba989a6-befe-4faa-9882-1e26c663c627 · outbound

This paper cites DeepSeek-V3 Technical Report.

Mixture-of-Experts Serving DeepSeek-V3 Technical Report

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.886414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.886414Z digest=sha256:a0fe02d0cd2c96883bf01f4a951a9a1af5d46fb3202f89a8b22f0dd7bf00d90f

Observation c1e10450-6fb9-4896-9034-0e133bb5d944 · outbound

This paper cites Manasse, Lyle A.

Mixture-of-Experts Serving Manasse, Lyle A

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.377074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.904175Z digest=sha256:ba949a51ca7edadf28d98c95d5b04829222a768a432d5c2bb5d893ef3874a563

Observation d992ddbb-3b98-45c8-a990-0c1c6c4b7215 · outbound

This paper cites Almost-polynomial ratio eth-hardness of approximating densest k- subgraph.

Mixture-of-Experts Serving Almost-polynomial ratio eth-hardness of approximating densest k- subgraph

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.364378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.908575Z digest=sha256:fb362d9d30a9211529e8d2e45d18c78f7b67367d49002cf29eff2a52d3bd7376

Observation 6958ac0b-6146-41ef-bb05-5022d4c02442 · outbound

This paper cites Nonclairvoyant scheduling.Theoretical computer science, 130(1):17–47, 1994.

Mixture-of-Experts Serving Nonclairvoyant scheduling.Theoretical computer science, 130(1):17–47, 1994

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.352007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.911733Z digest=sha256:869acdb524e60227eca32ef09ec3d49187f75653dcb0d4bc09d3a8f78a9b36b5

Observation 0cbdf1c4-7e39-41b1-9d46-e09073266e28 · outbound

This paper cites Chasing convex bodies optimally.

Mixture-of-Experts Serving Chasing convex bodies optimally

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.338820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.915056Z digest=sha256:574e07cd22387da3b5c0da3e347201eb65f467d404efbd0239e593293c186014

Observation 90fe9938-959e-436e-8569-3747348ded41 · outbound

This paper cites Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.

Mixture-of-Experts Serving Outrageously large neural networks: The sparsely-gated mixture-of-experts layer

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.918963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.918963Z digest=sha256:8861e3eedc26598a189372f622dd760f7b52f6a26589e92e297a367a55c4c431

Observation 4875a2c9-4685-424d-8c54-d5b66cc25cca · outbound

This paper cites Amortized efficiency of list update and paging rules.

Mixture-of-Experts Serving Amortized efficiency of list update and paging rules

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.316182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.923267Z digest=sha256:3f8af396e55a437b330ea66a6c9f0ecb5b4acb10adaec6d41ebaabb39898324b

Observation 2e8f9ee3-575f-432b-a1ae-2c3c47199131 · outbound

This paper cites Scheduling a single batch processing machine with non-identical job sizes.The International Journal of Production Research, 32(7):1615–1635, 1994.

Mixture-of-Experts Serving Scheduling a single batch processing machine with non-identical job sizes.The International Journal of Production Research, 32(7):1615–1635, 1994

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.293374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.926760Z digest=sha256:e8326741620cc4edcc13d82dafb59eef238d2c0222a813a24f958b6af9448630

Observation 7fb6e405-dcab-4fb9-be5a-386235643ee9 · outbound

This paper cites LLM Serving Optimization with Variable Prefill and Decode Lengths.

Mixture-of-Experts Serving LLM Serving Optimization with Variable Prefill and Decode Lengths

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-15T15:48:23.929970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:48:23.929970Z digest=sha256:4dcf4f4bccee06967ef81f6b01f808c63aac6d0cc4b09b3287ef0f9f1ef428df

Observation 25616e1c-cb30-4dc1-95a3-73c3e3102d75 · outbound

This paper cites FastServe:Iteration-Level preemptive scheduling for large language model inference.

Mixture-of-Experts Serving FastServe:Iteration-Level preemptive scheduling for large language model inference

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.261846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.934062Z digest=sha256:d859ef39560395104b6f01853cbfc5b108bb2f1bb30af84c420e42d1abcc5054

Observation 77aadf28-6e2c-4cfa-b36e-87345503e3ef · outbound

This paper cites Orca: A distributed serving system for Transformer-Based generative models.

Mixture-of-Experts Serving Orca: A distributed serving system for Transformer-Based generative models

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:48:24.237415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T15:48:23.938414Z digest=sha256:6cc08364011c43f3a03de71982334b66eea3441448b31a496126e855560bbfb0

Pith citing papers

Observation 4cd430e3-9734-4038-98e0-98c33048b18f · inbound

TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes cites this paper.

TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes Mixture-of-Experts Serving

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-15T17:51:06.541624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-15T17:51:05.684119Z digest=sha256:fa1ebd85d1a8082113e3b8b4f6fc7570240b28a0bef79dbbefc3f8f71ea91180