Related papers: Sequence-Aware Split Heuristic to Mitigate SM Unde…

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…

Efficiently training LLMs with long sequences is important yet challenged by the massive computation and memory requirements. Sequence parallelism has been proposed to tackle these problems, but existing methods suffer from scalability or…

As AI workloads drive increasing memory requirements, domain-specific accelerators need higher-density on-chip memory beyond what current SRAM scaling trends can provide. Simultaneously, the vast amounts of short-lived data in these…

Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…

We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing. In contrast to the traditional span-based decoding, where spans are combined only based on the sum of their scores, we…

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU…

The paper proposes a new text recognition network for scene-text images. Many state-of-the-art methods employ the attention mechanism either in the text encoder or decoder for the text alignment. Although the encoder-based attention yields…

Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. However, despite the high speedups they offer, speculative decoding methods often achieve…

Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the dominant decode-time bottlenecks. While sparse attention reduces computation and transfer…

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single-GPU inference becomes inefficient due to increased latency…

Existing methods for training LLMs on long-sequence data, such as Tensor Parallelism and Context Parallelism, exhibit low Model FLOPs Utilization as sequence lengths and number of GPUs increase, especially when sequence lengths exceed 1M…

As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention computation is dominated by a small subset of tokens. This…

Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A promising approach is to leverage sparsity in attention.…

In this work, we analyze efficient window shift schemes for windowed decoding of spatially coupled low-density parity-check (SC-LDPC) codes, which is known to yield close-tooptimal decoding results when compared to full belief propagation…

Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on semantic image segmentation. One common way to extract multi-scale features is to feed…

Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature…

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…