Related papers: DuQuant++: Fine-grained Rotation Enhances Microsca…

Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large Language Models (LLMs). Global rotation methods achieve inference efficiency by fusing…

Pre-training Transformers in FP4 precision is becoming a promising approach to gain substantial speedup, but it comes with a considerable loss of accuracy. Microscaling (MX) data format provides a fine-grained per-group quantization method…

Diffusion transformers have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challenges for practical deployment.…

Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of…

Diffusion models can effectively generate high-quality images. However, as they scale, rising memory demands and higher latency pose substantial deployment challenges. In this work, we aim to accelerate diffusion models by quantizing their…

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Microscaling data formats leverage per-block tensor quantization to enable aggressive model compression with limited loss in accuracy. Unlocking their potential for efficient training and inference necessitates hardware-friendly…

Recent research implies that training and inference of deep neural networks (DNN) can be computed with low precision numerical representations of the training/test data, weights and gradients without a general loss in accuracy. The benefit…

Quantization for deep neural networks (DNNs) is the process of mapping the parameter values of DNNs from original data types to other data types of lower precision to reduce model sizes and make inference faster. Quantization often maps…

Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats. Intuitively, finer block sizes should yield lower quantization error; however, a paradox recently…

The demand for inference on extremely large scale LLMs has seen enormous growth in the recent months. It made evident the colossal shortage of dedicated hardware capable of efficient and fast processing of the involved compute and memory…

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant…

The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. In this work, we propose methods that learn fusible rotations…

Existing weight-activation quantization methods for Large Language Models (LLMs) primarily address channel-wise outliers but often neglect token-wise outliers, which limits the accuracy of quantized models. In this work, we propose…

Existing low-bit Microscaling (MX) formats, such as MXFP4, often suffer from substantial accuracy degradation due to the use of a shared scaling factor with the Power-of-Two format. In this work, we explore strategies that introduce minimal…

The increasing computational demands of foundation models have spurred research into low-precision training, with 4-bit floating-point (\texttt{FP4}) formats emerging as a frontier for maximizing hardware throughput. While numerous…

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on integer quantization,…

The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs. Yet, existing quantized training methods still…

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs: coarse-grained ($\textit{e.g.,}$ channel-wise) quantization…