REVIEW 9 cited by
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
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
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
read the original abstract
Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs poses significant challenges for existing approaches due to varying popularity of LLMs. In the paper, we present MuxServe, a flexible spatial-temporal multiplexing system for efficient multiple LLM serving. The key insight behind is to colocate LLMs considering their popularity to multiplex memory resources, and leverage the characteristics of prefill and decoding phases to separate and flexibly colocate them to multiplex computation resources. MuxServe formally formulates the multiplexing problem, and proposes a novel placement algorithm and adaptive batch scheduling strategy to identify optimal colocations and maximize utilization. MuxServe designs a unified resource manager to enable flexible and efficient multiplexing. Evaluation results show that MuxServe can achieves up to $1.8\times$ higher throughput or processes $2.9\times$ more requests within $99\%$ SLO attainment. The code is available at: \url{https://github.com/hao-ai-lab/MuxServe}.
Forward citations
Cited by 9 Pith papers
-
Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes
An ACK-latched epoch protocol lets a hard-barriered CPU LLM inference gang change membership per token bit-exactly and Pareto-dominate static core partitions on general throughput.
-
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
KVServe delivers up to 9.13x job completion time speedup and 32.8x time-to-first-token reduction by making KV cache compression service-aware and adaptive in disaggregated LLM serving.
-
CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving
Layer-wise data-parallel replication of hot Transformer layers onto reclaimed idle GPUs reduces LLM serving cold-start latency 97.9–99.3% and average latency 20.7–28.1% while attaining 100% SLO on production traces.
-
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
KV-cache serving systems concentrate into five archetypes under a four-axis taxonomy, with ownership explaining residual distributed design variance and seven measurement gaps blocking next steps.
-
JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
JigsawRL achieves up to 1.85x higher throughput in LLM RL pipelines via pipeline multiplexing, sub-stage graphs, and look-ahead scheduling compared to prior systems.
-
Valve: Production Online-Offline Inference Colocation with Jointly-Bounded Preemption Latency and Rate
Valve jointly bounds preemption latency and rate for online-offline LLM colocation on GPUs, delivering 34.6% higher cluster utilization and a 2,170-GPU saving in a production deployment of 8,054 GPUs with under 5% TTF...
-
InstantInfer: Enabling Fast LLM Cold Start with Communicating Finite Automata
InstantInfer refactors vLLM's cold start into a concurrent state-machine pipeline, speeding up startup by up to 7.2×.
-
FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location
FlexNPU is a transparent virtualization system for Ascend NPUs that supports dynamic prefill-decode co-location in LLM serving and reports throughput gains plus large TTFT reductions versus static baselines.
-
FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters
FlexPipe introduces runtime pipeline refactoring for LLMs to achieve higher resource efficiency and lower latency in serverless GPU clusters with fragmentation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.