ProQuant is a weight‑only post‑training quantization framework designed for Mixture‑of‑Experts large language models. It introduces PoP, which jointly prunes experts and assigns mixed‑precision bit‑widths to better use a tight bit budget, and RoCo, a routing‑consistent RMSNorm fine‑tune that mitigates routing drift caused by quantization errors. Experiments show ProQuant outperforms existing methods on a range of generative tasks.
arXiv:2606. 04980v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory.
The paper introduces Colla-Q, a Mixture-of-Experts (MoE) quantization technique that uses activation entropy to allocate bit-widths across experts. By balancing performance among experts, Colla-Q improves overall MoE accuracy and reduces reliance on calibration datasets. The method aims to maintain robustness and stability in quantized MoE models.
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
arXiv:2605. 26660v2 Announce Type: replace Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
arXiv:2602. 06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.
The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
The paper examines weight-only post‑training quantization (PTQ) and finds that minimizing reconstruction loss does not always improve model performance, sometimes even harming it on calibration data. It shows that weights with low reconstruction loss on one distribution can perform worse when activation distributions shift. To address this, the authors introduce Distributionally Robust Quantization (DRQ), a refinement step that minimizes worst‑case reconstruction loss over a constrained set of activation distributions while keeping the quantization grid unchanged. Experiments demonstrate that DRQ improves models quantized by several PTQ methods across dense and mixture‑of‑experts large language models, offering better downstream performance without extra inference cost.
GAMMA is a post‑training framework that learns module‑wise precision preferences for mixed‑precision quantization of large language models. It optimizes a teacher‑forced hidden‑state reconstruction objective under an augmented Lagrangian constraint and then projects the learned preferences into exact budget‑feasible discrete assignments via integer programming. Because the learned preferences encode a stable sensitivity ranking, a single training run can be reused for any deployment budget, reducing per‑budget adaptation from hours to minutes and outperforming fixed‑precision baselines and search‑based methods on Llama and Qwen models.
arXiv:2607. 23047v1 Announce Type: cross Abstract: Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget.
arXiv:2607. 06601v1 Announce Type: cross Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: Mixture-of-Experts (MoE) sparsifies the FFN, Mixture-of-Depths (MoD) skips whole transformer blocks, and KV-cache quantization compresses attention memory.
arXiv:2606. 05688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale foundation models efficiently by activating only a subset of experts for each token, but their large number of expert parameters still makes quantization essential for practical deployment.