Related papers: Quartet II: Accurate LLM Pre-Training in NVFP4 by …

Using fewer bits to represent model parameters and related tensors during pre-training has become a required technique for improving GPU efficiency without sacrificing accuracy. Microscaling (MX) formats introduced in NVIDIA Blackwell…

As GPU architectures rapidly evolve to meet the growing demands of exascale computing and machine learning, the performance implications of architectural innovations remain poorly understood across diverse workloads. NVIDIA Blackwell (B200)…

Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive training costs make Post-Training Quantization (PTQ) a more practical…

Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. This makes them highly appropriate for systems with limited resources and low power capacity.…

The advent of ultra-low-bit LLM models (1/1.58/2-bit), which match the perplexity and end-task performance of their full-precision counterparts using the same model size, is ushering in a new era of LLM inference for resource-constrained…

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

This work targets the commonly used FPGA (field-programmable gate array) devices as the hardware platform for DNN edge computing. We focus on DNN quantization as the main model compression technique. The novelty of this work is: We use a…

Quantization-Aware Training (QAT) integrates quantization into the training loop, enabling LLMs to learn robust low-bit representations, and is widely recognized as one of the most promising research directions. All current QAT research…

Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can further bring more considerable acceleration, since the backward…

While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly…

There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on…

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…

Large-scale language models (LLMs) excel in language processing tasks but face deployment challenges due to high memory and computational demands. While low-bit quantization, such as 4-bit techniques, offers a potential solution, these…

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher…

Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger…

As large language models continue to scale, low-bit weight-only post-training quantization (PTQ) offers a practical solution to their memory-efficient deployment. Although block-wise PTQ is capable of matching the full-precision (FP)…