Ying Xu

Guanchen Li, Yixing Xu, Zeping Li et al.

Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) yet often fails to maintain comparable performance. Local pruning performs efficient layer-by-layer compression but ignores global topology. Although global pruning aims to identify an optimal sparse model, intuitive methods typically adopt a two-stage paradigm that first evaluates substructure saliency and then applies global pruning, which ignores inter-structure dependencies and fails to achieve end-to-end optimization. To address these limitations, we propose Týr-the-Pruner, an efficient end-to-end search-based global structural pruning framework. This framework constructs a supernet by repeatedly applying local pruning across a range of sparsity ratios to each layer in an LLM, with the core goal of determining the optimal sparsity distribution under a target overall sparsity ratio. Concretely, we introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction. Furthermore, we employ an iterative prune-and-search strategy with coarse-to-fine sparsity granularity to ensure efficient search convergence. Experimental results show that Týr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance while removing a challenging 50% of Llama-3.1-70B's parameters. Code will be available at https://github.com/AMD-AGI/Tyr-the-Pruner.

Yixing Xu, Chao Li, Xuanwu Yin et al.

Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific downstream tasks. However, the model trained based on LoRA often has an unsatisfactory performance due to its low-rank assumption. In this paper, we propose a novel method called Dual LoRA to improve the performance by incorporating an inductive bias into the original LoRA. Specifically, we separate low-rank matrices into two groups: the magnitude group to control whether or not and how far we should update a parameter and the direction group to decide whether this parameter should move forward or backward, to better simulate the parameter updating process of the full fine-tuning based on gradient-based optimization algorithms. We show that this can be simply achieved by adding a ReLU function to the magnitude group and a sign function to the direction group. We conduct several experiments over a wide range of NLP tasks, including natural language generation (NLG), understanding (NLU), and commonsense reasoning datasets on GPT-2, RoBERTa, DeBERTa, and LLaMA-1/2/3 as baseline models. The results show that we consistently outperform LoRA and its state-of-the-art variants with the same number of trainable parameters.

Haiduo Huang, Fuwei Yang, Zhenhua Liu et al.

Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to predict multiple tokens, which are then verified in parallel by the larger target model. However, the limited capacity of the draft model often necessitates tree-based sampling to improve prediction accuracy, where multiple candidates are generated at each step. We identify a key limitation in this approach: the candidates at the same step are derived from the same representation, limiting diversity and reducing overall effectiveness. To address this, we propose Jakiro, leveraging Mixture of Experts (MoE), where independent experts generate diverse predictions, effectively decoupling correlations among candidates. Furthermore, we introduce a hybrid inference strategy, combining autoregressive decoding for initial tokens with parallel decoding for subsequent stages, and enhance the latter with contrastive mechanism in features to improve accuracy. Our method significantly boosts prediction accuracy and achieves higher inference speedups. Extensive experiments across diverse models validate the effectiveness and robustness of our approach, establishing a new SOTA in speculative decoding. Our codes are available at https://github.com/haiduo/Jakiro.

Huanxuan Liao, Yixing Xu, Shizhu He et al.

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address this issue by compressing the KV cache along the temporal axis through strategies such as token eviction or merging to reduce memory and computational overhead. However, these methods often neglect fine-grained importance variations across feature dimensions (i.e., the channel axis), thereby limiting their ability to effectively balance efficiency and model accuracy. In reality, we observe that channel saliency varies dramatically across both queries and positions: certain feature channels carry near-zero information for a given query, while others spike in relevance. To address this oversight, we propose SPARK, a training-free plug-and-play method that applies unstructured sparsity by pruning KV at the channel level, while dynamically restoring the pruned entries during attention score computation. Notably, our approach is orthogonal to existing KV compression and quantization techniques, making it compatible for integration with them to achieve further acceleration. By reducing channel-level redundancy, SPARK enables processing of longer sequences within the same memory budget. For sequences of equal length, SPARK not only preserves or improves model accuracy but also reduces KV cache storage by over 30% compared to eviction-based methods. Furthermore, even with an aggressive pruning ratio of 80%, SPARK maintains performance with less degradation than 5% compared to the baseline eviction method, demonstrating its robustness and effectiveness. Our code will be available at https://github.com/Xnhyacinth/SparK.

Jinze Li, Yixing Xu, Haiduo Huang et al.

Speculative decoding (SPD) aims to accelerate the auto-regressive token generation process of a target Large Language Model (LLM). Some approaches employ a draft model with multiple heads to predict a sequence of future tokens, where each head handles a token in the sequence. The target LLM verifies the predicted sequence and accepts aligned tokens, enabling efficient multi-token generation. However, existing methods assume that all tokens within a sequence are equally important, employing identical head structures and relying on a single-generation paradigm, either serial or parallel. To this end, we theoretically demonstrate that initial tokens in the draft sequence are more important than later ones. Building on this insight, we propose Gumiho, a hybrid model combining serial and parallel heads. Specifically, given the critical importance of early tokens, we employ a sophisticated Transformer architecture for the early draft heads in a serial configuration to improve accuracy. For later tokens, we utilize multiple lightweight MLP heads operating in parallel to enhance efficiency. By allocating more advanced model structures and longer running times to the early heads, Gumiho achieves improved overall performance. The experimental results demonstrate that our method outperforms existing approaches, fully validating its effectiveness.

Hao Jiang, Yixing Xu, Pradeep Varakantham

The Ride-Pool Matching Problem (RMP) is central to on-demand ride-pooling services, where vehicles must be matched with multiple requests while adhering to service constraints such as pickup delays, detour limits, and vehicle capacity. Most existing RMP solutions assume passengers are picked up and dropped off at their original locations, neglecting the potential for passengers to walk to nearby spots to meet vehicles. This assumption restricts the optimization potential in ride-pooling operations. In this paper, we propose a novel matching method that incorporates extended pickup and drop-off areas for passengers. We first design a tree-based approach to efficiently generate feasible matches between passengers and vehicles. Next, we optimize vehicle routes to cover all designated pickup and drop-off locations while minimizing total travel distance. Finally, we employ dynamic assignment strategies to achieve optimal matching outcomes. Experiments on city-scale taxi datasets demonstrate that our method improves the number of served requests by up to 13\% and average travel distance by up to 21\% compared to leading existing solutions, underscoring the potential of leveraging passenger mobility to significantly enhance ride-pooling service efficiency.

Yixing Xu, Shivank Nag, Dong Li et al.

Transformer-based LLMs have achieved exceptional performance across a wide range of NLP tasks. However, the standard self-attention mechanism suffers from quadratic time complexity and linearly increased cache size. Sliding window attention (SWA) solves this problem by restricting the attention range to a fixed-size local context window. Nevertheless, SWA employs a uniform window size for each head in each layer, making it inefficient in capturing context of varying scales. To mitigate this limitation, we propose Multi-Scale Window Attention (MSWA) which applies diverse window sizes across heads and layers in the Transformer. It not only allows for different window sizes among heads within the same layer but also progressively increases window size allocation from shallow to deep layers, thus enabling the model to capture contextual information with different lengths and distances. Experimental results on language modeling and common-sense reasoning tasks substantiate that MSWA outperforms traditional local attention in both effectiveness and efficiency.

Jinze Li, Yixing Xu, Guanchen Li et al.

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in parallel from a smaller draft model, yet its strict exact-match verification discards many semantically valid continuations. Moreover, existing training-based SPD methods often suffer from performance degradation on out-of-distribution (OOD) tasks. To this end, we propose Training-Free Loosely Speculative Decoding (FLy), a novel method that loosens the rigid verification criterion by leveraging the target model's self-corrective behavior to judge whether a draft-target mismatch remains semantically valid. FLy introduces a two-tier mechanism: an entropy-level gate that identifies whether the current token allows multiple plausible alternatives or is nearly deterministic, and a token-level deferred window that distinguishes genuine errors from differently worded yet semantically correct variants. To further reduce latency, we design a multi-level acceleration strategy that accelerates not only the target model but also the drafter itself. Owing to its training-free design, FLy composes seamlessly with arbitrary draft-target pairs and generalizes across models and domains without hyperparameter re-tuning. Experiments show that FLy preserves more than 99% of the target model's accuracy while achieving an average 2.81x speedup on Llama-3.1-70B-Instruct and 5.07x speedup on the 405B variant. Notably, on out-of-domain datasets, our method remains highly effective and outperforms the training-based method EAGLE-3 by 1.62x.