# Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments

arXiv: https://arxiv.org/abs/2411.17741 · HTML: https://mlsanity.com/paper/2411.17741/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 24 Nov 2024.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 29 of 29)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [Efficient LLM Scheduling by Learning to Rank](https://mlsanity.com/paper/2408.15792/) (2024)
- [Punica: Multi-Tenant LoRA Serving](https://mlsanity.com/paper/2310.18547/) (2023)
- [Fairness in Serving Large Language Models](https://mlsanity.com/paper/2401.00588/) (2023)
- [LoRA-Pro: Are Low-Rank Adapters Properly Optimized?](https://mlsanity.com/paper/2407.18242/) (2024)
- [Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference](https://mlsanity.com/paper/2403.20306/) (2024)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (2024)
- [ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching](https://mlsanity.com/paper/2403.17312/) (2024)
- [ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference](https://mlsanity.com/paper/2404.07947/) (2024)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)
- [ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention](https://mlsanity.com/paper/2211.05109/) (2022)
- [Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization](https://mlsanity.com/paper/2406.12930/) (2024)
- [CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference](https://mlsanity.com/paper/2401.11240/) (2024)
- [Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System](https://mlsanity.com/paper/2403.06664/) (2024)

## Built on by (most cited first, 9 of 9)

- [Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management](https://mlsanity.com/paper/2505.03756/) (2025)
- [Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems](https://mlsanity.com/paper/2511.22880/) (2025)
- [ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache](https://mlsanity.com/paper/2604.06370/) (2026)
- [A Data-driven ML Approach for Maximizing Performance in LLM-Adapter Serving](https://mlsanity.com/paper/2508.08343/) (2025)
- [DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution](https://mlsanity.com/paper/2603.19248/) (2026)
- [Symbiosis: Multi-Adapter Inference and Fine-Tuning](https://mlsanity.com/paper/2507.03220/) (2025)
- [Data Driven Optimization of GPU efficiency for Distributed LLM-Adapter Serving](https://mlsanity.com/paper/2602.24044/) (2026)
- [Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling](https://mlsanity.com/paper/2607.25498/) (2026)
- [Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services](https://mlsanity.com/paper/2609.23321/) (2026)

## Abstract (arXiv)

The widespread adoption of LLMs has driven an exponential rise in their deployment, imposing substantial demands on inference clusters. These clusters must handle numerous concurrent queries for different LLM downstream tasks. To handle multi-task settings with vast LLM parameter counts, methods like Low-Rank Adaptation (LoRA) enable task-specific fine-tuning while sharing most of the base LLM model across tasks. Hence, they allow concurrent task serving with minimal memory requirements. However, existing LLM serving systems face inefficiencies: they overlook workload heterogeneity, impose high link bandwidth from frequent adapter loading, and suffer from head-of-line blocking in their schedulers. To address these challenges, we present Chameleon, a novel LLM serving system optimized for many adapter environments, that relies on two core ideas: adapter caching and adapter-aware scheduling. First, Chameleon caches popular adapters in GPU memory, minimizing the adapter loading times. Importantly, it uses the otherwise idle GPU memory, avoiding extra memory costs. Second, Chameleon uses a non-preemptive multi-queue scheduling to efficiently account for workload heterogeneity. In this way, Chameleon simultaneously prevents head of line blocking and starvation. We implement Chameleon on top of a state-of-the-art LLM serving platform and evaluate it with real-world production traces and open-source LLMs. Under high loads, Chameleon reduces P99 and P50 TTFT latency by 80.7% and 48.1%, respectively, while improving throughput by 1.5x compared to state-of-the-art baselines.