# LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind

arXiv: https://arxiv.org/abs/2508.15601 · HTML: https://mlsanity.com/paper/2508.15601/

## Key facts

- Cited by 10 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 30 of its 67 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## 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 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification](https://mlsanity.com/paper/2405.14256/) (2024)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [TurboTransformers: An Efficient GPU Serving System For Transformer Models](https://mlsanity.com/paper/2010.05680/) (2020)
- [HexGen: Generative Inference of Large Language Model over Heterogeneous Environment](https://mlsanity.com/paper/2311.11514/) (2023)
- [Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production](https://mlsanity.com/paper/2211.10017/) (2022)
- [Benchmarking and Dissecting the Nvidia Hopper GPU Architecture](https://mlsanity.com/paper/2402.13499/) (2024)
- [ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments](https://mlsanity.com/paper/2502.09334/) (2025)
- [QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference](https://mlsanity.com/paper/2402.10076/) (2024)
- [AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization](https://mlsanity.com/paper/2409.16546/) (2024)

## Built on by (most cited first, 10 of 10)

- [SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs](https://mlsanity.com/paper/2509.25390/) (2025)
- [GTM: Simulating the World of Tools for AI Agents](https://mlsanity.com/paper/2512.04535/) (2025)
- [Parallax: Efficient LLM Inference Service over Decentralized Environment](https://mlsanity.com/paper/2509.26182/) (2025)
- [BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2602.10729/) (2026)
- [DARE: Diffusion Large Language Models Alignment and Reinforcement Executor](https://mlsanity.com/paper/2604.04215/) (2026)
- [Bench360: Benchmarking Local LLM Inference from 360 Degrees](https://mlsanity.com/paper/2511.16682/) (2025)
- [OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration](https://mlsanity.com/paper/2602.12151/) (2026)
- [RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks](https://mlsanity.com/paper/2608.12004/) (2026)
- [Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics](https://mlsanity.com/paper/2604.07144/) (2026)
- [Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference](https://mlsanity.com/paper/2605.13915/) (2026)

## Abstract (arXiv)

Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. However, existing systems struggle to (i) automatically generalize across diverse hardware architectures and precision formats, often requiring fragmented, hand-tuned kernels, and (ii) fully exploit available memory and compute resources, often causing performance bottlenecks. To address these problems, we propose TurboMind, a generalizable and efficient mixed-precision LLM inference engine of LMDeploy. TurboMind is built around two hardware-aware mixed-precision pipelines: A General Matrix Multiply (GEMM) pipeline that optimizes matrix operations through offline weight packing and online acceleration, and an attention pipeline that enables efficient attention computation with different Query, Key, and Value precision combinations. These pipelines are enabled by four key techniques: (i) Hardware-aware weight packing and (ii) adaptive head alignment for generalizability, and (iii) instruction-level parallelism and (iv) a KV memory loading pipeline for efficiency. We conduct comprehensive evaluations of LMDeploy powered by TurboMind across sixteen popular LLMs and four representative GPU architectures. Results demonstrate that LMDeploy achieves up to 61% lower serving latency (30% on average) and up to 156% higher throughput (58% on average) in mixed-precision workloads compared to existing mixed-precision frameworks, establishing consistent performance improvements across all tested configurations and hardware types. This work is open-sourced and publicly available at https://github.com/InternLM/lmdeploy.