arXiv:2606. 09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Large Language Models (LLMs), but activation quantization remains difficult because outlier-dominated channels lead to large quantization errors.
arXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains...
arXiv:2606. 10890v1 Announce Type: cross Abstract: Post-training quantization (PTQ) compresses large language models by mapping weights to low-bit representations.
arXiv:2610.00983v1 Announce Type: cross Abstract: Post-training quantization (PTQ) methods typically use sequential quantization that partitions a pre-trained LLM into a series of units (e.g., transf...
arXiv:2602. 03120v2 Announce Type: replace-cross Abstract: Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune.
ConQuR introduces a lightweight post‑training rotation calibration for large language model activation quantization. By learning orthogonal rotations that align normalized activations with the corners of an inscribed hypercube, the method distributes activation energy evenly and can be updated online without storing activations. Experiments on Llama‑2 and Llama‑3 models (3B–70B) show competitive or improved perplexity and reasoning performance while avoiding costly training or large offline storage.
arXiv:2606. 07618v1 Announce Type: cross Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales.
Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity.
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv:2607. 21446v1 Announce Type: new Abstract: Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent.
arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,...
arXiv:2608. 05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights.
arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.