Pith. sign in

REVIEW 9 cited by

LLM Inference Serving: Survey of Recent Advances and Opportunities

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.12391 v1 pith:7X2XVFCQ submitted 2024-07-17 cs.DC cs.AI

classification cs.DCcs.AI
keywords surveyrecentservingabreastadvancementsadvancesalteringcomprehensive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This survey offers a comprehensive overview of recent advancements in Large Language Model (LLM) serving systems, focusing on research since the year 2023. We specifically examine system-level enhancements that improve performance and efficiency without altering the core LLM decoding mechanisms. By selecting and reviewing high-quality papers from prestigious ML and system venues, we highlight key innovations and practical considerations for deploying and scaling LLMs in real-world production environments. This survey serves as a valuable resource for LLM practitioners seeking to stay abreast of the latest developments in this rapidly evolving field.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. When Is the Same Model Not the Same Service? A Measurement Study of Hosted Open-Weight LLM APIs

    cs.PF 2026-05 unverdicted novelty 7.0 of 10

    Hosted open-weight LLM APIs function as time-varying heterogeneous services rather than fixed model artifacts, with demand concentrated, supply-use mismatches, and task-specific routing yielding major cost and through...

  2. When Is the Same Model Not the Same Service? A Measurement Study of Hosted Open-Weight LLM APIs

    cs.PF 2026-05 conditional novelty 7.0 of 10

    Hosted open-weight LLMs function as heterogeneous, time-varying services rather than uniform model artifacts, with concentrated demand, decoupled supply and adoption, and measurable gains from task-aware routing.

  3. Sutradhara: An Intelligent Orchestrator-Engine Co-design for Tool-based Agentic Inference

    cs.DC 2026-01 unverdicted novelty 6.0 of 10

    Sutradhara co-designs orchestrator and LLM serving to overlap tool execution with prefill, stream tool dispatch during decode, and use semantic hints for cache management, yielding up to 77% higher load at fixed media...

  4. Adaptive LLM Routing under Budget Constraints

    cs.LG 2025-08 conditional novelty 6.0 of 10

    LLM routing is framed as a budget-constrained contextual bandit, solved by a preference-prior initialized LinUCB variant with an online multi-choice knapsack cost policy.

  5. InstantInfer: Enabling Fast LLM Cold Start with Communicating Finite Automata

    cs.DC 2026-07 conditional novelty 5.0 of 10

    InstantInfer refactors vLLM's cold start into a concurrent state-machine pipeline, speeding up startup by up to 7.2×.

  6. RAP: Runtime Adaptive Pruning for LLM Inference

    cs.LG 2025-05 unverdicted novelty 5.0 of 10

    RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.

  7. Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

    cs.AI 2026-05 unverdicted novelty 4.0 of 10

    Workload-aware optimizations for LLM serving in AML and fraud detection yield substantial gains in throughput, latency, and GPU utilization on synthetic compliance prompts.

  8. Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI

    cs.DC 2025-11 reject novelty 4.0 of 10

    A framework for runtime re-splitting and re-placement of foundation model layers across edge nodes is proposed, but its claimed latency gains are inherited from prior work rather than measured.

  9. From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap

    cs.SE 2024-10 unverdicted novelty 4.0 of 10

    A semi-structured thematic synthesis identifies core challenges in FM selection, alignment, prompting, orchestration, testing, deployment, and cross-cutting concerns like observability for production-ready FMware.

Pith tools