Related papers: Dissecting Outlier Dynamics in LLM NVFP4 Pretraini…
Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and…
Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this…
KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…
Multi-head Latent Attention (MLA) significantly reduces KVCache memory usage in Large Language Models while introducing substantial computational overhead and intermediate variable expansion. This poses challenges for efficient hardware…
Large language models require significant computational resources for deployment, making quantization essential for practical applications. However, the main obstacle to effective quantization lies in systematic outliers in activations and…
Modern Large Language Model serving system batches multiple requests to achieve high throughput, while batching attention operations is challenging, rendering memory bandwidth a critical bottleneck. The community relies on high-end GPUs…
Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often…
The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…
Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…
Deep Learning Accelerators are prone to faults which manifest in the form of errors in Neural Networks. Fault Tolerance in Neural Networks is crucial in real-time safety critical applications requiring computation for long durations. Neural…
Training large language models (LLMs) models directly in low-precision offers a way to address computational costs by improving both throughput and energy efficiency. For those purposes, NVIDIA's recent Blackwell architecture facilitates…
Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A…
Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered…
Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…
Transformers have emerged as the dominant neural-network architecture, achieving state-of-the-art performance in language processing and computer vision. At the core of these models lies the attention mechanism, which requires a nonlinear,…
Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining…
As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs…
Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…
Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized…