Challenge: Existing dynamic schemes such as early-exit and layer-drop reduce FLOPs but break batch processing or introduce KV-cache inconsistency.
Approach: They propose a dynamic low-rank substitution framework that employs a lightweight decision module at each layer to dynamically determine the execution branch for different tokens.
Outcome: The proposed model reduces computation by approximately 40% compared to the original dense model while outperforming existing baseline methods.

Similar Papers

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference (2025.naacl-short)

Copied to clipboard

Challenge: Recent studies have shown that sharing key-value (KV) cache across layers is effective in efficient inference of large language models.
Approach: They propose a unified framework that covers several recent methods and their novel variants to investigate cross-layer KV sharing.
Outcome: The proposed framework achieves higher throughput and better performance when reducing the size of the key-value cache by 2 while maintaining competitive performance.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Copied to clipboard

Challenge: Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach: They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome: The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.
Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Copied to clipboard

Challenge: Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach: They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome: The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.
KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to inference large language models are limited by CPU capabilities and memory constraints.
Approach: They propose an efficient I/O-aware LLM inference method that overlaps GPU computation with KV cache transfer to minimize idle GPU time.
Outcome: The proposed method reduces the cost of auto-regressive decoding by 35.8% . it also achieves 46.2% higher throughput during decoding compared to state-of-the-art methods.
River-LLM: Large Language Model Seamless Exit Based on KV Share (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to reduce latency and speed up early exits are costly and impose significant cost and energy consumption.
Approach: They propose a lightweight KV-Shared Exit River framework that allows the backbone’s missing KV cache to be naturally generated and preserved during the exit process.
Outcome: The proposed framework achieves 1.71 to 2.16 speedup while maintaining high generation quality.
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) with extended context windows are expensive and infeasible on fixed memory hardware due to the surprisingly large memory consumption of KV Cache.
Approach: They propose a general framework for long-context KV cache eviction that achieves more optimal and efficient evict in a single operation during the encoding phase.
Outcome: The proposed framework improves performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5 with over 95% performance maintenance.
Eigen Attention: Attention in Low-Rank Space for KV Cache Compression (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have been increasing context lengths to enhance their performance, but at long context length, the KV cache becomes the new bottleneck in memory usage during inference.
Approach: They propose an approach which performs the attention operation in a low-rank space and reduces the KV cache memory overhead.
Outcome: The proposed approach reduces the KV cache memory overhead and reduces memory usage with minimal drop in performance over OPT, MPT, and Llama model families.
TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference (2021.naacl-main)

Copied to clipboard

Challenge: Existing pre-trained language models (PLMs) are expensive in inference, making them impractical in resource-limited real-world applications.
Approach: They propose a dynamic token reduction approach to accelerate PLMs' inference by adapting the layer number of each token to avoid redundant calculation.
Outcome: The proposed approach speeds up BERT by 2-5 times and improves performance in long-text tasks with less computation.
RefreshKV: Updating Small KV Cache During Long-form Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for generating long sequences of tokens are expensive and require memory and computation resources.
Approach: They propose a method that alternates between full context attention and attention over a subset of input tokens during generation.
Outcome: The proposed method achieves comparable speedup to eviction-based methods while improving performance for various long-form generation tasks.
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are a powerful tool for high-performance inference serving.
Approach: They focus on system-aware KV infrastructure for serving LLMs . they analyze cross-behavior co-design affinity and behavior-objective links .
Outcome: The proposed key-value (KV) cache is crucial for low-latency, high-throughput LLM inference serving.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations