Related papers: Qrita: High-performance Top-k and Top-p using Pivo…

Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders inference efficiency, and prior studies have shown that many…

Major challenges in LLMs inference remain frequent memory bandwidth bottlenecks, computational redundancy, and inefficiencies in long-sequence processing. To address these issues, we propose LLM-CoOpt, a comprehensive algorithmhardware…

Diffusion Transformers (DiTs) incur prohibitive computational costs due to the quadratic scaling of self-attention. Existing pruning methods fail to simultaneously satisfy differentiability, efficiency, and the strict static budgets…

Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs.…

Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video…

Vision Transformers (ViT) have recently demonstrated success across a myriad of computer vision tasks. However, their elevated computational demands pose significant challenges for real-world deployment. While low-rank approximation stands…

The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However,…

Top-K masking schemes have been proposed as a method to promote sparse representations in Information Retrieval (IR) tasks, as a simple alternative to Floating Point Operations per Second (FLOPS) regularization. Algorithms such as Bilingual…

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which…

Large-scale linear programs (LPs) arise in many decision systems, including ranking, allocation, and matching problems that must be solved repeatedly at massive scale. Prior work such as ECLIPSE and LinkedIn's open-source DuaLip showed that…

Recent advances in low-rank adaptation (LoRA) have enabled efficient fine-tuning of large language models (LLMs) with minimal additional parameters. However, existing LoRA methods apply static rank configurations uniformly across all input…

Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model…

We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. QLoRA backpropagates gradients through a…

Latent Dirichlet Allocation(LDA) is a popular topic model. Given the fact that the input corpus of LDA algorithms consists of millions to billions of tokens, the LDA training process is very time-consuming, which may prevent the usage of…

Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements. Our research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to…

Pre-trained language models (PLMs) have shown their effectiveness in multiple scenarios. However, KBQA remains challenging, especially regarding coverage and generalization settings. This is due to two main factors: i) understanding the…

Plackett-Luce gradient estimation enables the optimization of stochastic ranking models within feasible time constraints through sampling techniques. Unfortunately, the computational complexity of existing methods does not scale well with…

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to improve their reasoning capabilities on complex tasks. This enables them to act as intelligent agents interacting with the real world. The recently…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their inference efficiency remains a critical bottleneck due to rapidly growing parameters. Recent advances in dynamic computation…