Xiaonan Song | Searcharxiv

arXiv2026

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions still show limitations of either non-negligible accuracy drop or low system efficiency. In this paper, we propose MixLLM that explores the optimization space of mixed-precision quantization between output features, based on the insight that different features matter differently in the model. MixLLM identifies the important output features in the global view rather than within each single layer, effectively assigning larger bit-width to output features that need it the most to achieve high accuracy and low memory usage. We present the sweet spot of quantization configuration of algorithm-system co-design with high accuracy and system efficiency. To address the system challenge, we design the two-step dequantization to make use of the Tensor Core easily and fast data type conversion to reduce dequantization overhead, and present the software pipeline to overlap the memory access, dequantization and the MatMul to the best. Extensive experiments show that with only 10\% more bits, the perplexity increase can be reduced from about 0.5 in SOTA to within 0.2 for Llama 3.1 70B, while MMLU-Pro loss can be reduced from 1.92 to 0.99 over the SOTA of three popular models. Besides its superior accuracy, MixLLM also achieves state-of-the-art system efficiency. Code is released at https://github.com/microsoft/MixLLM.

cs.LG↗

arXiv2025

Efficient Vision-Language Reasoning via Adaptive Token Pruning

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism that retains only the most informative tokens based on contextual relevance. ATP operates at the vision-language interface, assigning a hybrid importance score combining ViT CLS attention (intra-modal saliency) and CLIP text-image similarity (inter-modal relevance) to keep top-K tokens for the LLM. Unlike static compression, ATP adapts to each input without modifying the backbone. Proposed as a lightweight gating module, ATP is compatible with popular backbones like BLIP-2, LLaVA, and Flamingo. Preliminary evaluations across VQAv2, GQA, and COCO indicate that ATP reduces inference FLOPs by around 40% and achieves roughly 1.5x speedups in end-to-end latency with negligible accuracy loss (less than 1%). Qualitative analyses suggest ATP preserves visual grounding and enhances interpretability. Beyond efficiency, we investigate robustness under corruptions; observations suggest adaptive pruning suppresses spurious correlations, improving stability. These findings imply that resource-constrained inference and model reliability are not competing objectives. Finally, we discuss ATP's role in efficient multimodal edge computing pipelines.

cs.CV↗