# BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models

arXiv: https://arxiv.org/abs/2404.18322 · HTML: https://mlsanity.com/paper/2404.18322/

## Key facts

- Cited by 5 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 33 of its 56 references that are in the map.
- First posted on arXiv 28 Apr 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, 30 of 33)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation](https://mlsanity.com/paper/2106.03164/) (2021)
- [SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference](https://mlsanity.com/paper/2307.02628/) (2023)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [PaSS: Parallel Speculative Sampling](https://mlsanity.com/paper/2311.13581/) (2023)
- [InferCept: Efficient Intercept Support for Augmented Large Language Model Inference](https://mlsanity.com/paper/2402.01869/) (2024)
- [Stitchable Neural Networks](https://mlsanity.com/paper/2302.06586/) (2023)

## Built on by (most cited first, 5 of 5)

- [Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2503.16585/) (2025)
- [FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models](https://mlsanity.com/paper/2508.01506/) (2025)
- [Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM](https://mlsanity.com/paper/2601.06627/) (2026)
- [Efficient Large Language Models with Zero-Shot Adjustable Acceleration](https://mlsanity.com/paper/2509.01190/) (2025)
- [HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads](https://mlsanity.com/paper/2608.19395/) (2026)

## Abstract (arXiv)

The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial challenges due to their high computational and memory demands. We introduce BlockLLM, a serving system that leverages component sharing among fine-tuned LLM models to provide an efficient and flexible solution for LLM workloads. BlockLLM partitions models into finer-grained blocks, enabling the reuse of model components and independent provisioning to improve computation efficiency. BlockLLM comprises an offline block zoo for storing blocks and an online system to serve requests through chains of blocks. It offers multi-fold flexibilities: (1) Adaptive assembly of blocks on-the-fly through equivalence evaluation among blocks in the zoo; (2) Per-block batch size configuration and best-effort KV cache coordination at the individual block level; (3) Speculative execution and locality-aware block placement to reduce communication costs from dynamic block resource allocation. Our evaluation shows that BlockLLM reduces memory and storage footprints and improves computational efficiency, outperforming existing serving approach in 95%ile latency and GPU utilization by 33.5% and 20.1%, respectively, with minimal impact on accuracy