Junqing Lin — accepted AI-conference papers

2026

CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints

Han Li, Jingwei Sun, Junqing Lin, Guangzhong Sun

AAAI 2026technical

Mixture of Experts (MoE) models have emerged as a promising approach to scale language models efficiently by activating only a subset of parameters for each input. However, deploying these models under GPU memory constraints remains challenging, as existing offloading strategies incur significant ov

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language Models

Mingge Lu, Jingwei Sun, Junqing Lin, Zechun Zhou, Guangzhong Sun

NeurIPS 2025poster

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their extensive parameter scales pose significant challenges for practical deployment. Unstructured pruning has emerged as an effective model compression strategy with minimal performance loss, which introduces fine-grained…

Cited by 0 Source ↗Scholar ↗