# Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference

arXiv: https://arxiv.org/abs/2503.23294 · HTML: https://mlsanity.com/paper/2503.23294/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in KV cache quantization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Placed in

- Efficient LLM inference and serving / [KV cache quantization](https://mlsanity.com/inference/kv-cache-quantization/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization](https://mlsanity.com/paper/2402.18096/) (2024)

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

- [MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts](https://mlsanity.com/paper/2506.07533/) (2025)
- [Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs](https://mlsanity.com/paper/2604.04722/) (2026)
- [Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving](https://mlsanity.com/paper/2511.06029/) (2025)
- [Runtime-Certified Bounded-Error Quantized Attention](https://mlsanity.com/paper/2605.20868/) (2026)
- [MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs](https://mlsanity.com/paper/2504.09504/) (2025)

## Abstract (arXiv)

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in LLMs based on token granularity, which is time-consuming in the search process and hardware inefficient during computation. This paper introduces a novel approach called Cocktail, which employs chunk-adaptive mixed-precision quantization to optimize the KV cache. Cocktail consists of two modules: chunk-level quantization search and chunk-level KV cache computation. Chunk-level quantization search determines the optimal bitwidth configuration of the KV cache chunks quickly based on the similarity scores between the corresponding context chunks and the query, maintaining the model accuracy. Furthermore, chunk-level KV cache computation reorders the KV cache chunks before quantization, avoiding the hardware inefficiency caused by mixed-precision quantization in inference computation. Extensive experiments demonstrate that Cocktail outperforms state-of-the-art KV cache quantization methods on various models and datasets.