PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce bottlenecks associated with memory bandwidth, but also increase end-to-end latency per inference run, requiring high speculation acceptance rates to improve performance. Combined with a variable rate of acceptance across tasks, speculative inference techniques can result in reduced performance. Additionally, pipeline-parallel designs require many user requests to maintain maximum utilization. As a remedy, we propose PipeInfer, a pipelined speculative acceleration technique to reduce inter-token latency and improve system utilization for single-request scenarios while also improving tolerance to low speculation acceptance rates and low-bandwidth interconnects. PipeInfer exhibits up to a 2.15$\times$ improvement in generation speed over standard speculative inference. PipeInfer achieves its improvement through Continuous Asynchronous Speculation and Early Inference Cancellation, the former improving latency and generation speed by running single-token inference simultaneously with several speculative runs, while the latter improves speed and latency by skipping the computation of invalidated runs, even in the middle of inference.

RAG vs. Long Context: Examining Frontier Large Language Models for Environmental Review Document Comprehension

Large Language Models (LLMs) have been applied to many research problems across various domains. One of the applications of LLMs is providing question-answering systems that cater to users from different fields. The effectiveness of LLM-based question-answering systems has already been established at an acceptable level for users posing questions in popular and public domains such as trivia and literature. However, it has not often been established in niche domains that traditionally require specialized expertise. To this end, we construct the NEPAQuAD1.0 benchmark to evaluate the performance of three frontier LLMs -- Claude Sonnet, Gemini, and GPT-4 -- when answering questions originating from Environmental Impact Statements prepared by U.S. federal government agencies in accordance with the National Environmental Environmental Act (NEPA). We specifically measure the ability of LLMs to understand the nuances of legal, technical, and compliance-related information present in NEPA documents in different contextual scenarios. For example, we test the LLMs' internal prior NEPA knowledge by providing questions without any context, as well as assess how LLMs synthesize the contextual information present in long NEPA documents to facilitate the question/answering task. We compare the performance of the long context LLMs and RAG powered models in handling different types of questions (e.g., problem-solving, divergent). Our results suggest that RAG powered models significantly outperform the long context models in the answer accuracy regardless of the choice of the frontier LLM. Our further analysis reveals that many models perform better answering closed questions than divergent and problem-solving questions.

MIREncoder: Multi-modal IR-based Pretrained Embeddings for Performance Optimizations

One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate Representations (IRs) for extracting features from source code. Most such works target specific tasks, or are designed with a pre-defined set of heuristics. So far, pre-trained models are rare in this domain, but the possibilities have been widely discussed. Especially approaches mimicking large-language models (LLMs) have been proposed. But these have prohibitively large training costs. In this paper, we propose MIREncoder, a M}ulti-modal IR-based Auto-Encoder that can be pre-trained to generate a learned embedding space to be used for downstream tasks by machine learning-based approaches. A multi-modal approach enables us to better extract features from compilable programs. It allows us to better model code syntax, semantics and structure. For code-based performance optimizations, these features are very important while making optimization decisions. A pre-trained model/embedding implicitly enables the usage of transfer learning, and helps move away from task-specific trained models. Additionally, a pre-trained model used for downstream performance optimization should itself have reduced overhead, and be easily usable. These considerations have led us to propose a modeling approach that i) understands code semantics and structure, ii) enables use of transfer learning, and iii) is small and simple enough to be easily re-purposed or reused even with low resource availability. Our evaluations will show that our proposed approach can outperform the state of the art while reducing overhead.

FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal search engines. Among these models, the Contrastive Language-Image Pre-training (CLIP) model has demonstrated remarkable performance in understanding and generating nuanced relationships between text and images. However, the conventional training of such models often requires centralized aggregation of vast datasets, posing significant privacy and data governance challenges. To address these concerns, this paper proposes a novel approach that leverages Federated Learning and parameter-efficient adapters, i.e., Low-Rank Adaptation (LoRA), to train VLMs. This methodology preserves data privacy by training models across decentralized data sources and ensures model adaptability and efficiency through LoRA's parameter-efficient fine-tuning. Our approach accelerates training time by up to 34.72 times and requires 2.47 times less memory usage than full fine-tuning.

SAM-I-Am: Semantic Boosting for Zero-shot Atomic-Scale Electron Micrograph Segmentation

Image segmentation is a critical enabler for tasks ranging from medical diagnostics to autonomous driving. However, the correct segmentation semantics - where are boundaries located? what segments are logically similar? - change depending on the domain, such that state-of-the-art foundation models can generate meaningless and incorrect results. Moreover, in certain domains, fine-tuning and retraining techniques are infeasible: obtaining labels is costly and time-consuming; domain images (micrographs) can be exponentially diverse; and data sharing (for third-party retraining) is restricted. To enable rapid adaptation of the best segmentation technology, we propose the concept of semantic boosting: given a zero-shot foundation model, guide its segmentation and adjust results to match domain expectations. We apply semantic boosting to the Segment Anything Model (SAM) to obtain microstructure segmentation for transmission electron microscopy. Our booster, SAM-I-Am, extracts geometric and textural features of various intermediate masks to perform mask removal and mask merging operations. We demonstrate a zero-shot performance increase of (absolute) +21.35%, +12.6%, +5.27% in mean IoU, and a -9.91%, -18.42%, -4.06% drop in mean false positive masks across images of three difficulty classes over vanilla SAM (ViT-L).

Learn and Search: An Elegant Technique for Object Lookup using Contrastive Learning

The rapid proliferation of digital content and the ever-growing need for precise object recognition and segmentation have driven the advancement of cutting-edge techniques in the field of object classification and segmentation. This paper introduces "Learn and Search", a novel approach for object lookup that leverages the power of contrastive learning to enhance the efficiency and effectiveness of retrieval systems. In this study, we present an elegant and innovative methodology that integrates deep learning principles and contrastive learning to tackle the challenges of object search. Our extensive experimentation reveals compelling results, with "Learn and Search" achieving superior Similarity Grid Accuracy, showcasing its efficacy in discerning regions of utmost similarity within an image relative to a cropped image. The seamless fusion of deep learning and contrastive learning to address the intricacies of object identification not only promises transformative applications in image recognition, recommendation systems, and content tagging but also revolutionizes content-based search and retrieval. The amalgamation of these techniques, as exemplified by "Learn and Search," represents a significant stride in the ongoing evolution of methodologies in the dynamic realm of object classification and segmentation.

Unsupervised learning based object detection using Contrastive Learning

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy environments. However, the collection of imagery itself can often be straightforward; for instance, cameras mounted in vehicles can effortlessly capture vast amounts of data in various real-world scenarios. In light of this, we introduce a groundbreaking method for training single-stage object detectors through unsupervised/self-supervised learning. Our state-of-the-art approach has the potential to revolutionize the labeling process, substantially reducing the time and cost associated with manual annotation. Furthermore, it paves the way for previously unattainable research opportunities, particularly for large, diverse, and challenging datasets lacking extensive labels. In contrast to prevalent unsupervised learning methods that primarily target classification tasks, our approach takes on the unique challenge of object detection. We pioneer the concept of intra-image contrastive learning alongside inter-image counterparts, enabling the acquisition of crucial location information essential for object detection. The method adeptly learns and represents this location information, yielding informative heatmaps. Our results showcase an outstanding accuracy of \textbf{89.2\%}, marking a significant breakthrough of approximately \textbf{15x} over random initialization in the realm of unsupervised object detection within the field of computer vision.

The Landscape and Challenges of HPC Research and LLMs

Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning. Both encoder-decoder models and prompt-based techniques have shown immense potential for natural language processing and code-based tasks. Over the past several years, many research labs and institutions have invested heavily in high-performance computing, approaching or breaching exascale performance levels. In this paper, we posit that adapting and utilizing such language model-based techniques for tasks in high-performance computing (HPC) would be very beneficial. This study presents our reasoning behind the aforementioned position and highlights how existing ideas can be improved and adapted for HPC tasks.

OMPGPT: A Generative Pre-trained Transformer Model for OpenMP

Large language models (LLMs), as epitomized by models like ChatGPT, have revolutionized the field of natural language processing (NLP). Along with this trend, code-based large language models such as StarCoder, WizardCoder, and CodeLlama have emerged, trained extensively on vast repositories of code data. Yet, inherent in their design, these models primarily focus on generative tasks like code generation, code completion, and comment generation, and general support for multiple programming languages. While the generic abilities of code LLMs are useful for many programmers, the area of high-performance computing (HPC) has a narrower set of requirements that make a smaller and more domain-specific LM a smarter choice. This paper introduces OMPGPT, a novel model meticulously designed to harness the inherent strengths of language models for OpenMP pragma generation. Furthermore, we adopt and adapt prompt engineering techniques from the NLP domain to create chain-of-OMP, an innovative strategy designed to enhance OMPGPT's effectiveness. Our extensive evaluations demonstrate that OMPGPT outperforms existing large language models specialized in OpenMP tasks and maintains a notably smaller size, aligning it more closely with the typical hardware constraints of HPC environments. We consider our contribution as a pivotal bridge, connecting the advantage of language models with the specific demands of HPC tasks. The success of OMPGPT lays a solid foundation, suggesting its potential applicability and adaptability to a wider range of HPC tasks, thereby opening new avenues in the field of computational efficiency and effectiveness.

LEFL: Low Entropy Client Sampling in Federated Learning

Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained by a central server that orchestrates the FL training process through a series of training rounds. In each round, the server samples clients from a client pool before sending them its latest global model parameters for further optimization. Naive sampling strategies implement random client sampling and fail to factor client data distributions for privacy reasons. Hence we proposes an alternative sampling strategy by performing a one-time clustering of clients based on their model's learned high-level features while respecting data privacy. This enables the server to perform stratified client sampling across clusters in every round. We show datasets of sampled clients selected with this approach yield a low relative entropy with respect to the global data distribution. Consequently, the FL training becomes less noisy and significantly improves the convergence of the global model by as much as 7.4% in some experiments. Furthermore, it also significantly reduces the communication rounds required to achieve a target accuracy.