Jingcun Wang

Jingcun Wang, Bing Li, Grace Li Zhang

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained platforms, e.g., edge devices. To address this challenge, in this paper, we propose a class-based early-exit for dynamic inference. Instead of pushing DNNs to make a dynamic decision at intermediate layers, we take advantage of the learned features in these layers to exclude as many irrelevant classes as possible, so that later layers only have to determine the target class among the remaining classes. When only one class remains at a layer, this class is the corresponding classification result. Experimental results demonstrate the computational cost of DNNs in inference can be reduced significantly with the proposed early-exit technique. The codes can be found at https://github.com/HWAI-TUDa/EarlyClassExclusion.

Xiaolin Lin, Jingcun Wang, Olga Kondrateva et al.

Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs. These methods ignore the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrading the performance of LLMs. To address this issue, we propose CompressKV, a resource-efficient KV-cache compression framework for GQA-based LLMs. Instead of aggregating attention scores from all heads, CompressKV identifies Semantic Retrieval Heads (SRHs) that capture both the initial and final tokens of a prompt and semantically important mid-context evidence, and uses them to select tokens whose KV pairs should be retained. Furthermore, CompressKV allocates cache budgets across layers according to offline estimates of layer-wise eviction error. Experiments on LongBench and Needle-in-a-Haystack show that CompressKV consistently outperforms existing KV-cache eviction methods across memory budgets. Notably, it preserves over 97\% of full-cache performance using only 3\% of the KV cache on LongBench question-answering tasks and achieves 90\% accuracy with just 0.7\% KV storage on Needle-in-a-Haystack. These results demonstrate an improved resource--performance trade-off for long-context LLM inference. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV

Xiaolin Lin, Jingcun Wang, Olga Kondrateva et al.

Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to memory and execution efficiency. Most KV cache compression methods rely on heuristic token eviction using all attention heads in Grouped Query Attention (GQA)-based LLMs. This method ignores the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrades the performance of LLMs. To address the issue above, instead of using all the attention heads in GQA-based LLMs to determine important tokens as in the previous work, we first identify the attention heads in each layer that are not only capable of retrieving the initial and final tokens of a prompt, but also capable of retrieving important tokens within the text and attending to their surrounding semantic context. Afterwards, we exploit such heads to determine the important tokens and retain their corresponding KV cache pairs. Furthermore, we analyze the cache eviction error of each layer individually and introduce a layer-adaptive KV cache allocation strategy. Experimental results demonstrate the proposed CompressKV consistently outperforms state-of-the-art approaches under various memory budgets on LongBench and Needle-in-a-Haystack benchmarks. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV.git.

Mengnan Jiang, Jingcun Wang, Amro Eldebiky et al.

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g., edge devices. To address the problem, pruning has been introduced to reduce the computational cost in executing DNNs. Previous pruning strategies are based on weight values, gradient values and activation outputs. Different from previous pruning solutions, in this paper, we propose a class-aware pruning technique to compress DNNs, which provides a novel perspective to reduce the computational cost of DNNs. In each iteration, the neural network training is modified to facilitate the class-aware pruning. Afterwards, the importance of filters with respect to the number of classes is evaluated. The filters that are only important for a few number of classes are removed. The neural network is then retrained to compensate for the incurred accuracy loss. The pruning iterations end until no filter can be removed anymore, indicating that the remaining filters are very important for many classes. This pruning technique outperforms previous pruning solutions in terms of accuracy, pruning ratio and the reduction of FLOPs. Experimental results confirm that this class-aware pruning technique can significantly reduce the number of weights and FLOPs, while maintaining a high inference accuracy.