---
title: "HeteroCache — paper by Shi et al. (2026) — summary and ideas"
description: "Storing keys and values for every token during long-context LLM generation consumes memory that grows linearly with input… 27 references."
authors: ["Zhiyuan Shi", "Qibo Qiu", "Xuefeng", "Zhonglin Jiang", "Li Yu", "Jian Jiang", "Xiaofei He", "Wenxiao Wang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1999/"
doi: "10.18653/v1/2026.acl-long.1999"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shi-2026-heterocache-dynamic-retrieval-approach-heterogeneous/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shi-2026-heterocache-dynamic-retrieval-approach-heterogeneous/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) / HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference

# HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference

**Authors:** Zhiyuan Shi, Qibo Qiu, Xuefeng, Zhonglin Jiang, Li Yu, Jian Jiang, [Xiaofei He](https://md.research.elamur.ai/free/en/authors/xiaofei-he/) and [Wenxiao Wang](https://md.research.elamur.ai/free/en/authors/wenxiao-wang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1999/) · [PDF](https://aclanthology.org/2026.acl-long.1999.pdf) · [DOI 10.18653/v1/2026.acl-long.1999](https://doi.org/10.18653/v1/2026.acl-long.1999) · [OpenAlex](https://openalex.org/W7166844924)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Storing keys and values for every token during long-context LLM generation consumes memory that grows linearly with input length. Static eviction methods such as SnapKV permanently discard tokens that may matter later. Dynamic methods such as ShadowKV and OmniKV can recall offloaded tokens, but they treat heads uniformly and fetch data from CPU memory at every step, which is slow. HeteroCache is a training-free framework built on two findings from a calibration study:

- **Temporal heterogeneity:** some attention heads keep a stable focus over many decoding steps, while others shift quickly.
- **Intralayer redundancy:** heads within the same layer often attend to nearly the same tokens.

An offline profiling step scores each head on stability and similarity and assigns it a role. A small set of representative heads keeps the full context on the GPU, and the remaining heads are compressed. Compressed heads whose attention drifts faster receive larger budgets. Most of the cache moves to CPU memory. Retrieval happens asynchronously and only when the full-context heads detect a meaningful attention shift. The authors report state-of-the-art accuracy on long-context benchmarks and substantially faster decoding, which matters for inference on limited hardware.

## Key points
- Evaluated on Llama and Qwen models and on the reasoning model DeepSeek-R1-Distill-Llama-8B, using LongBench, LongBench v2 and InfiniteBench at several compression rates.
- Decoding is roughly 3× faster than the uncompressed model at a 224K context and over 40× faster than OmniKV. Prefill latency (TTFT) is essentially unchanged.
- From 128K tokens onward, HeteroCache has the lowest per-token latency of all compared compression methods.
- Head stability and similarity are measured with the overlap coefficient between top-k attention index sets. Ablations show that removing either the stability-based budget allocation or the dynamic retrieval hurts accuracy, and 0.5 was chosen as the threshold.
- The prototype uses plain PyTorch without custom CUDA kernels, so its speed also depends on CPU–GPU bandwidth such as PCIe. Code is available at github.com/ponytaill/HeteroCache.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 172 works · 12,988 citations
- [China Mobile](https://md.research.elamur.ai/free/en/companies/china-mobile/) — Company, Beijing, China · 9 works · 21 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 242 works

## Cite

Cite as: Zhiyuan Shi, Qibo Qiu, Xuefeng, Zhonglin Jiang, Li Yu, Jian Jiang, Xiaofei He and Wenxiao Wang. 2026. HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shi2026heterocache,
  title = {{HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference}},
  author = {Zhiyuan Shi, Qibo Qiu, Xuefeng, Zhonglin Jiang, Li Yu, Jian Jiang, Xiaofei He and Wenxiao Wang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1999},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1999}
}
```

- [← previous HERMeS: Human Evaluation & Ranking of MultiplE Systems](https://md.research.elamur.ai/free/en/papers/vanhorn-2026-hermes-human-evaluation-ranking-multiple/)
- [next → Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?](https://md.research.elamur.ai/free/en/papers/renduchintala-2026-heterogeneity-formal-linguistic-competence-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/)

## References

27 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Javed Aslam, Ekaterina Pelekhov, and Daniela Rus. 2004. The star clustering algorithm for static and dynamic information organization. Journal of Graph Algorithms and Applications, 8(1):95–129. [find](https://scholar.google.com/scholar?q=Javed+Aslam%2C+Ekaterina+Pelekhov%2C+and+Daniela+Rus%2E+2004%2E+The+star+clustering+algorithm+for+static+and+dynamic+information+organization%2E+Journal+of+Graph+Algorithms+and+Applications%2C+8%281%29%3A95%E2%80%93129%2E)
2. Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2024. LongBench: A bilingual, multi-task benchmark for long context understanding. In Proceedings of the 62nd Annual Meeting of the Associat… [find](https://scholar.google.com/scholar?q=Yushi+Bai%2C+Xin+Lv%2C+Jiajie+Zhang%2C+Hongchang+Lyu%2C+Jiankai+Tang%2C+Zhidian+Huang%2C+Zhengxiao+Du%2C+Xiao+Liu%2C+Aohan+Zeng%2C+Lei+Hou%2C+Yuxiao+Dong%2C+Jie+Tang%2C+and+Juanzi+Li%2E+2024%2E+LongBench%3A+A+bilingual%2C+multi%2Dtask)
3. Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2025. [LongBench v2: Towards deeper understanding and reasoning on realistic long-context multitasks](https://md.research.elamur.ai/free/en/papers/bai-2024-longbench-v2-deeper-understanding/). In Proceedings of the 63rd Annual Meeting of the Associa…
4. Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Yucheng Li, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Junjie Hu, and Wen Xiao. 2025. [Pyramidkv: Dynamic kv cache compression based on pyramidal information funneling](https://md.research.elamur.ai/free/en/papers/cai-2024-pyramidkv-dynamic-kv-cache-compression/). Preprint, arXiv:2406.02069.
5. Ziyang Chen, Xing Wu, Junlong Jia, Chaochen Gao, Qi Fu, Debing Zhang, and Songlin Hu. 2026. Longbench pro: A more realistic and comprehensive bilingual long-context evaluation benchmark. Preprint, arXiv:2601.02872. and Xia Hu. 2024. [Kivi: A tuning-free asymmetric 2bit quantization for kv cache](https://md.research.elamur.ai/free/en/papers/liu-2024-kivi-tuning-free-asymmetric-2bit/). arXi…
6. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025. Deepseek-v3 technical report. Preprint, arXiv:2… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+Dejian+Yang%2C+Deli+Chen%2C+Dongjie+Ji%2C+Erhan)
7. Ziran Qin, Yuchen Cao, Mingbao Lin, Wen Hu, Shixuan Fan, Ke Cheng, Weiyao Lin, and Jianguo Li. 2025. Cake: Cascading and adaptive kv cache eviction with layer preferences. arXiv preprint arXiv:2503.12491. — [arXiv:2503.12491](https://arxiv.org/abs/2503.12491) [find](https://scholar.google.com/scholar?q=Ziran+Qin%2C+Yuchen+Cao%2C+Mingbao+Lin%2C+Wen+Hu%2C+Shixuan+Fan%2C+Ke+Cheng%2C+Weiyao+Lin%2C+and+Jianguo+Li%2E+2025%2E+Cake%3A+Cascading+and+adaptive+kv+cache+eviction+with+layer+preferences%2E+arXiv+preprint+arXiv%3A2503%2E12)
8. Tim Dettmers, Mike Lewis, Sam Shleifer, and Luke Zettlemoyer. 2021. [8-bit optimizers via block-wise quantization](https://md.research.elamur.ai/free/en/papers/dettmers-2021-8-bit-optimizers-block-wise/). arXiv preprint arXiv:2110.02861.
9. Yao Fu, Rameswar Panda, Xinyao Niu, Xiang Yue, Hannaneh Hajishirzi, Yoon Kim, and Hao Peng. 2024. [Data engineering for scaling language models to 128k context](https://md.research.elamur.ai/free/en/papers/fu-2024-data-engineering-scaling-language-models/). Preprint, arXiv:2402.10171.
10. Yunfan Gao, Yun Xiong, Wenlong Wu, Bohan Li, Yijie Zhong, and Haofen Wang. 2026. U-niah: Unified rag and llm evaluation for long context needle-in-a-haystack. ACM Trans. Inf. Syst., 44(3). [find](https://scholar.google.com/scholar?q=Yunfan+Gao%2C+Yun+Xiong%2C+Wenlong+Wu%2C+Bohan+Li%2C+Yijie+Zhong%2C+and+Haofen+Wang%2E+2026%2E+U%2Dniah%3A+Unified+rag+and+llm+evaluation+for+long+context+needle%2Din%2Da%2Dhaystack%2E+ACM+Trans%2E+Inf%2E+Syst%2E%2C+44%283%29%2E)
11. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, and 175 others. 2025. Deepseek-r1 incentivizes reasoning in llms through rein… [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Peiyi+Wang%2C+Qihao+Zhu%2C+Runxin+Xu%2C+Ruoyu+Zhang%2C+Shirong+Ma%2C+Xiao+Bi%2C+Xiaokang+Zhang%2C+Xingkai+Yu%2C+Yu+Wu%2C+Z%2E+F%2E+Wu%2C+Zhibin+Gou%2C+Zhihong+Shao%2C+Zhuoshu+Li)
12. Jitai Hao, Yuke Zhu, Tian Wang, Jun Yu, Xin Xin, Bo Zheng, Zhaochun Ren, and Sheng Guo. 2025. Omnikv: Dynamic context selection for efficient long-context llms. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jitai+Hao%2C+Yuke+Zhu%2C+Tian+Wang%2C+Jun+Yu%2C+Xin+Xin%2C+Bo+Zheng%2C+Zhaochun+Ren%2C+and+Sheng+Guo%2E+2025%2E+Omnikv%3A+Dynamic+context+selection+for+efficient+long%2Dcontext+llms%2E+In+The+Thirteenth+International+Confere)
13. Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W Mahoney, Yakun S Shao, Kurt Keutzer, and Amir Gholami. 2024. [Kvquant: Towards 10 million context length llm inference with kv cache quantization](https://md.research.elamur.ai/free/en/papers/hooper-2024-kvquant-towards-10-million-context/). Advances in Neural Information Processing Systems, 37:1270–1303.
14. Huiqiang Jiang, Yucheng Li, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir H. Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2024. [Minference 1.0: accelerating pre-filling for long-context llms via dynamic sparse attention](https://md.research.elamur.ai/free/en/papers/jiang-2024-minference-1-0-accelerating-pre/). In Proceedings of the 38th Internati…
15. Yuhong Li, Yingbing Huang, Bowen Yang, Bharat Venkitesh, Acyr Locatelli, Hanchen Ye, Tianle Cai, Patrick Lewis, and Deming Chen. 2024. [Snapkv: Llm knows what you are looking for before generation](https://md.research.elamur.ai/free/en/papers/li-2024-snapkv-llm-knows-looking-before/). Advances in Neural Information Processing Systems, 37:22947–22970.
16. Zirui Liu, Jiayi Yuan, Hongye Jin, Shaochen Zhong, Zhaozhuo Xu, Vladimir Braverman, Beidi Chen, Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr… — [OpenAI GPT-5 System Card](https://md.research.elamur.ai/free/en/papers/singh-2025-openai-gpt-5-system-card/)
17. Hanshi Sun, Li-Wen Chang, Wenlei Bao, Size Zheng, Ningxin Zheng, Xin Liu, Harry Dong, Yuejie Chi, and Beidi Chen. 2025. Shadowkv: Kv cache in shadows for high-throughput long-context llm inference. Preprint, arXiv:2410.21465. [find](https://scholar.google.com/scholar?q=Hanshi+Sun%2C+Li%2DWen+Chang%2C+Wenlei+Bao%2C+Size+Zheng%2C+Ningxin+Zheng%2C+Xin+Liu%2C+Harry+Dong%2C+Yuejie+Chi%2C+and+Beidi+Chen%2E+2025%2E+Shadowkv%3A+Kv+cache+in+shadows+for+high%2Dthroughput+long%2Dcontext+llm+inference%2E+Pr)
18. Dezydery Szymkiewicz. 1934. Une conlribution statistique à la géographie floristique. Acta Societatis Botanicorum Poloniae, 11(3):249–265. [find](https://scholar.google.com/scholar?q=Dezydery+Szymkiewicz%2E+1934%2E+Une+conlribution+statistique+%C3%A0+la+g%C3%A9ographie+floristique%2E+Acta+Societatis+Botanicorum+Poloniae%2C+11%283%29%3A249%E2%80%93265%2E)
19. Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, and Song Han. 2024. [Quest: Query-aware sparsity for efficient long-context llm inference](https://md.research.elamur.ai/free/en/papers/tang-2024-quest-query-aware-sparsity-efficient/). arXiv preprint arXiv:2406.10774.
20. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazari… — [Gemini: A Family of Highly Capable Multimodal Models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/)
21. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
22. Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, and 5 others. 2025. [Openhands: An open platform f…](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/)
23. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Streamingllm: Efficient streaming language models with attention sinks. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Yuandong+Tian%2C+Beidi+Chen%2C+Song+Han%2C+and+Mike+Lewis%2E+2023%2E+Streamingllm%3A+Efficient+streaming+language+models+with+attention+sinks%2E+In+International+Conference+on+Learning+Representatio)
24. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
25. Zihao Ye, Lequn Chen, Ruihang Lai, Wuwei Lin, Yi-neng Zhang, Stephanie Wang, Tianqi Chen, Baris Kasikci, Vinod Grover, Arvind Krishnamurthy, and Luis Ceze. 2025. Flashinfer: Efficient and customizable attention engine for llm inference serving. Preprint, arXiv:2501.01005. [find](https://scholar.google.com/scholar?q=Zihao+Ye%2C+Lequn+Chen%2C+Ruihang+Lai%2C+Wuwei+Lin%2C+Yi%2Dneng+Zhang%2C+Stephanie+Wang%2C+Tianqi+Chen%2C+Baris+Kasikci%2C+Vinod+Grover%2C+Arvind+Krishnamurthy%2C+and+Luis+Ceze%2E+2025%2E+Flashinfer%3A+Efficient+and+customizable)
26. Xinrong Zhang, Yingfa Chen, Shengding Hu, Zihang Xu, Junhao Chen, Moo Hao, Xu Han, Zhen Thai, Shuo Wang, Zhiyuan Liu, and Maosong Sun. 2024. ∞Bench: Extending long context evaluation beyond 100K tokens. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volum… [find](https://scholar.google.com/scholar?q=Xinrong+Zhang%2C+Yingfa+Chen%2C+Shengding+Hu%2C+Zihang+Xu%2C+Junhao+Chen%2C+Moo+Hao%2C+Xu+Han%2C+Zhen+Thai%2C+Shuo+Wang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2024%2E+%E2%88%9EBench%3A+Extending+long+context+evaluation+beyond+100K+token)
27. Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, and Beidi Chen. 2023. H2o: heavy-hitter oracle for efficient generative inference of large language models. In Proceedings of the 37th Internationa… [find](https://scholar.google.com/scholar?q=Zhenyu+Zhang%2C+Ying+Sheng%2C+Tianyi+Zhou%2C+Tianlong+Chen%2C+Lianmin+Zheng%2C+Ruisi+Cai%2C+Zhao+Song%2C+Yuandong+Tian%2C+Christopher+R%C3%A9%2C+Clark+Barrett%2C+Zhangyang+Wang%2C+and+Beidi+Chen%2E+2023%2E+H2o%3A+heavy%2Dhitter+oracle+)

*Updated 1 November 2026*