Paper Citation Record · LEDGER

DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 46 inbound Pith citation observations for arXiv:2401.08671.

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

pith.paper-citation-record.v1
2401.08671 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 46 of 46 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:27:17.268072Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T11:59:50.582581Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 9ea946e8-56ae-4cfe-9859-67f8ea75d258 · inbound

A Survey on Efficient Inference for Large Language Models cites this paper.

A Survey on Efficient Inference for Large Language Models DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 279

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:39:33.490879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 852d3521-7c90-462c-832a-bcc96f884e8b · inbound

HybridFlow: A Flexible and Efficient RLHF Framework cites this paper.

HybridFlow: A Flexible and Efficient RLHF Framework DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:53:38.983721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 816fb079-be1e-4d89-b5fb-5e5ad5510036 · inbound

Ensuring Fair LLM Serving Amid Diverse Applications cites this paper.

Ensuring Fair LLM Serving Amid Diverse Applications DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T13:44:18.524777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91aa30dc-2c98-4911-8bd1-504ade85231f · inbound

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching cites this paper.

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T13:36:43.930205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a129fb99-037a-4081-a384-96d4579e7a79 · inbound

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching cites this paper.

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-23T16:58:11.937207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c8721d8-0d08-4ff2-ad35-51587c21c02f · inbound

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design cites this paper.

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:57:40.262382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5c526a61-35fc-4073-9207-c18d2d746ee0 · inbound

Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels cites this paper.

Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:05:22.498348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba259c45-6fa6-4ff5-9025-48c8fcdfd722 · inbound

Efficiently Scaling LLM Reasoning with Certaindex cites this paper.

Efficiently Scaling LLM Reasoning with Certaindex DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T23:09:44.472681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4346f9de-5e52-4366-852c-485d078ea07e · inbound

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding cites this paper.

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T17:39:10.292188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9565420e-dca0-4ebd-8b5b-4b53a0e33883 · inbound

iServe: An Intent-based Serving System for LLMs cites this paper.

iServe: An Intent-based Serving System for LLMs DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T21:37:14.252651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0a45e8e-b80a-420d-b3ee-031f62db8e6d · inbound

KVDirect: Distributed Disaggregated LLM Inference cites this paper.

KVDirect: Distributed Disaggregated LLM Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T15:56:14.577889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca8c0a0-3680-428a-9ec0-d540affbe1ac · inbound

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline cites this paper.

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T17:55:54.042509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bedb766-c3d8-4009-a6f4-8cabf5d05c7c · inbound

Memory Offloading for Large Language Model Inference with Latency SLO Guarantees cites this paper.

Memory Offloading for Large Language Model Inference with Latency SLO Guarantees DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T10:10:22.872509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebbd282c-edd5-43e1-ae96-9cf2bf0587d4 · inbound

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference cites this paper.

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:17:08.081299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d2c85ef4-c9e7-4393-b965-2be97d35296d · inbound

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference cites this paper.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.268072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 096efbf6-39e3-4d39-a19d-496313f4af06 · inbound

Taming the Titans: A Survey of Efficient LLM Inference Serving cites this paper.

Taming the Titans: A Survey of Efficient LLM Inference Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T05:49:09.813521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f0a985d-a116-40b9-8d50-f3648ef4cc2f · inbound

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage cites this paper.

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:45:34.325191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c79d06-ef02-4f26-9420-a0d9059c4842 · inbound

Ascendra: Dynamic Request Prioritization for Efficient LLM Serving cites this paper.

Ascendra: Dynamic Request Prioritization for Efficient LLM Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:23:26.935869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b06f25c7-381a-4421-a4e4-1855b33a2e6f · inbound

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production cites this paper.

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:44:58.084998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 313443c8-0e08-4e59-b929-60f45ebddbc7 · inbound

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity cites this paper.

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:50:52.961383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17c4b2d3-7d80-4f7e-a321-478c29739989 · inbound

Rectified Sparse Attention cites this paper.

Rectified Sparse Attention DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:48.938385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f75106c-2cda-4921-a977-c6699722549e · inbound

Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems cites this paper.

Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:19:10.069938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f846ec65-36d7-4250-8207-3cbfadd1c795 · inbound

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics cites this paper.

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T16:21:09.103693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804a2c0c-1dc3-47dc-a9f9-82497e7d3e21 · inbound

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference cites this paper.

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:29.009532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c81406e8-a4fc-4464-adde-fb4e1b76914f · inbound

WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving cites this paper.

WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-22T12:24:51.224216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 268c5e27-d697-4056-a7a9-becc9c17b726 · inbound

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems cites this paper.

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:15:06.799217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ffa085a0-9695-41a7-8065-f41d1ffbd4c5 · inbound

FASTER: Rethinking Real-Time Flow VLAs cites this paper.

FASTER: Rethinking Real-Time Flow VLAs DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T08:05:15.319681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aaf05164-07a0-4f3b-a171-ee9197516154 · inbound

FASTER: Rethinking Real-Time Flow VLAs cites this paper.

FASTER: Rethinking Real-Time Flow VLAs DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T10:50:01.062812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9c00d7a0-282f-44cf-acd1-f1192872aa99 · inbound

Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies cites this paper.

Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:43:00.670264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 876815a3-5aa7-486c-8378-6ce3c7e3a195 · inbound

Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows cites this paper.

Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:30:00.274373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d57681e3-f3fb-42fc-8982-ad26d7846e04 · inbound

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines cites this paper.

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:59:03.464710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 61b831f4-fcd0-47ff-adc3-18b849d53a70 · inbound

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities cites this paper.

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:10.210742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c0ab0b09-ffc3-4798-9256-856c3064c131 · inbound

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems cites this paper.

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:35:35.686543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bdb1d749-6c65-4651-bbda-4dec91c8d58d · inbound

Federation of Experts: Communication Efficient Distributed Inference for Large Language Models cites this paper.

Federation of Experts: Communication Efficient Distributed Inference for Large Language Models DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.551006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4baef794-3b5c-4841-b783-3006804077fb · inbound

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion cites this paper.

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:23:14.150643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 13fd3d8f-a36d-4899-832c-359a99beb400 · inbound

AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System cites this paper.

AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-25T03:15:17.294037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 83d9298f-7b54-40a6-9b32-f483749567fe · inbound

Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving cites this paper.

Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-02T00:56:25.651067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6e215635-2261-408f-9102-c420675d9305 · inbound

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving cites this paper.

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:36:26.302619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f690c26d-f209-43f4-b662-660346d06641 · inbound

Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference cites this paper.

Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:27:06.039657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e407d765-5959-43a4-b272-097e3e6cc9fa · inbound

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents cites this paper.

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:36:59.463922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 338310bb-7333-4cb7-9032-c6507b74679f · inbound

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving cites this paper.

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:39:24.932913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a6e62147-93fa-408e-88c6-1da34df551c8 · inbound

LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs cites this paper.

LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-04T11:59:50.585382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 286d72a8-abb5-474e-8411-d1aa48d0e656 · inbound

SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering cites this paper.

SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:27:14.671196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 208c00e4-9b51-4ca6-a064-f638bf559b5f · inbound

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving cites this paper.

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-12T09:50:23.266920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03ec011-2f9d-4d74-9362-1893d5dec339 · inbound

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving cites this paper.

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T05:43:12.690359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0422bac-16ce-46b9-823a-0e3a1899cb82 · inbound

Beyond Storage: State as a Runtime Control Problem in Parallel and Distributed Systems cites this paper.

Beyond Storage: State as a Runtime Control Problem in Parallel and Distributed Systems DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T19:51:06.098713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.