# ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

arXiv: https://arxiv.org/abs/2502.14317 · HTML: https://mlsanity.com/paper/2502.14317/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [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)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth](https://mlsanity.com/paper/2103.03404/) (2021)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [When Attention Sink Emerges in Language Models: An Empirical View](https://mlsanity.com/paper/2410.10781/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [Data Engineering for Scaling Language Models to 128K Context](https://mlsanity.com/paper/2402.10171/) (2024)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Attention Sorting Combats Recency Bias In Long Context Language Models](https://mlsanity.com/paper/2310.01427/) (2023)
- [KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation](https://mlsanity.com/paper/2205.09921/) (2022)
- [Parallel Context Windows for Large Language Models](https://mlsanity.com/paper/2212.10947/) (2022)
- [Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration](https://mlsanity.com/paper/2406.15765/) (2024)
- [Training-Free Long-Context Scaling of Large Language Models](https://mlsanity.com/paper/2402.17463/) (2024)
- [Contextual Position Encoding: Learning to Count What's Important](https://mlsanity.com/paper/2405.18719/) (2024)
- [ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities](https://mlsanity.com/paper/2407.14482/) (2024)

## Built on by (most cited first, 14 of 14)

- [SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning](https://mlsanity.com/paper/2506.01713/) (2025)
- [CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning](https://mlsanity.com/paper/2508.07871/) (2025)
- [Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel](https://mlsanity.com/paper/2509.25913/) (2025)
- [SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving](https://mlsanity.com/paper/2505.23932/) (2025)
- [Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS](https://mlsanity.com/paper/2507.05557/) (2025)
- [SAS: Simulated Attention Score](https://mlsanity.com/paper/2507.07694/) (2025)
- [Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data](https://mlsanity.com/paper/2510.25804/) (2025)
- [SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining](https://mlsanity.com/paper/2602.10718/) (2026)
- [Self-Adjust Softmax](https://mlsanity.com/paper/2502.18277/) (2025)
- [ATTS: Asynchronous Test-Time Scaling via Conformal Prediction](https://mlsanity.com/paper/2509.15148/) (2025)
- [BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models](https://mlsanity.com/paper/2602.04163/) (2026)
- [CodeComp: Structural KV Cache Compression for Agentic Coding](https://mlsanity.com/paper/2604.10235/) (2026)
- [Beyond Sparse Weights: When Is Attention Compressible?](https://mlsanity.com/paper/2608.21541/) (2026)
- [Prefilling-dLLM v2: Learned Chunk Routing for Long-Context Diffusion Language Models](https://mlsanity.com/paper/2610.17868/) (2026)

## Abstract (arXiv)

Extrapolating ultra-long contexts (text length >128K) remains a major challenge for large language models (LLMs), as most training-free extrapolation methods are not only severely limited by memory bottlenecks, but also suffer from the attention sink, which restricts their scalability and effectiveness in practice. In this work, we propose ParallelComp, a parallel long-context compression method that effectively overcomes the memory bottleneck, enabling 8B-parameter LLMs to extrapolate from 8K to 128K tokens on a single A100 80GB GPU in a training-free setting. ParallelComp splits the input into chunks, dynamically evicting redundant chunks and irrelevant tokens, supported by a parallel KV cache eviction mechanism. Importantly, we present a systematic theoretical and empirical analysis of attention biases in parallel attention-including the attention sink, recency bias, and middle bias-and reveal that these biases exhibit distinctive patterns under ultra-long context settings. We further design a KV cache eviction technique to mitigate this phenomenon. Experimental results show that ParallelComp enables an 8B model (trained on 8K context) to achieve 91.17% of GPT-4's performance under ultra-long contexts, outperforming closed-source models such as Claude-2 and Kimi-Chat. We achieve a 1.76x improvement in chunk throughput, thereby achieving a 23.50x acceleration in the prefill stage with negligible performance loss and pave the way for scalable and robust ultra-long contexts extrapolation in LLMs. We release the code at https://github.com/menik1126/ParallelComp.