Pie: Pooling CPU Memory for LLM Inference

The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill over to CPU memory; however, traditional GPU-CPU memory swapping often results in higher latency and lower throughput. This paper introduces Pie, an LLM inference framework that addresses these challenges with performance-transparent swapping and adaptive expansion. By leveraging predictable memory access patterns and the high bandwidth of modern hardware like the NVIDIA GH200 Grace Hopper Superchip, Pie enables concurrent data swapping without affecting foreground computation, expanding effective memory without added latency. Adaptive expansion dynamically adjusts CPU memory allocation based on real-time information, optimizing memory usage and performance under varying conditions. Pie maintains low computation latency, high throughput, and high elasticity. Our experimental evaluation demonstrates that Pie achieves optimal swapping policy during cache warmup and effectively balances increased memory capacity with negligible impact on computation. With its extended capacity, Pie outperforms vLLM by up to 1.9X in throughput and 2X in latency. Additionally, Pie can reduce GPU memory usage by up to 1.67X while maintaining the same performance. Compared to FlexGen, an offline profiling-based swapping solution, Pie achieves magnitudes lower latency and 9.4X higher throughput.

SkyServe: Serving AI Models across Regions and Clouds with Spot Instances

Recent years have witnessed an explosive growth of AI models. The high cost of hosting AI services on GPUs and their demanding service requirements, make it timely and challenging to lower service costs and guarantee service quality. While spot instances have long been offered with a large discount, spot preemptions have discouraged users from using them to host model replicas when serving AI models. To address this, we introduce SkyServe, a system that efficiently serves AI models over a mixture of spot and on-demand replicas across regions and clouds. SkyServe intelligently spreads spot replicas across different failure domains (e.g., regions or clouds) to improve availability and reduce correlated preemptions, overprovisions cheap spot replicas than required as a safeguard against possible preemptions, and dynamically falls back to on-demand replicas when spot replicas become unavailable. We compare SkyServe with both research and production systems on real AI workloads: SkyServe reduces cost by up to 44% while achieving high resource availability compared to using on-demand replicas. Additionally, SkyServe improves P50, P90, and P99 latency by up to 2.6x, 3.1x, 2.7x compared to other research and production systems.

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

Text summarization is an essential task to help readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models are unable to efficiently process long text commonly seen in the summarization problem domain. In this paper, we propose Summ^N, a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context lengths of typical pretrained LMs. Summ^N first generates the coarse summary in multiple stages and then produces the final fine-grained summary based on them. The framework can process input text of arbitrary length by adjusting the number of stages while keeping the LM context size fixed. Moreover, it can deal with both documents and dialogues and can be used on top of any underlying backbone abstractive summarization model. Our experiments demonstrate that Summ^N significantly outperforms previous state-of-the-art methods by improving ROUGE scores on three long meeting summarization datasets AMI, ICSI, and QMSum, two long TV series datasets from SummScreen, and a newly proposed long document summarization dataset GovReport. Our data and code are available at https://github.com/chatc/Summ-N.

DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization

Transformer-based models have achieved state-of-the-art performance on short text summarization. However, they still struggle with long-input summarization. In this paper, we present a new approach for long-input summarization: Dynamic Latent Extraction for Abstractive Summarization. We jointly train an extractor with an abstractor and treat the extracted text snippets as the latent variable. We propose extractive oracles to provide the extractor with a strong learning signal. We introduce consistency loss, which encourages the extractor to approximate the averaged dynamic weights predicted by the generator. We conduct extensive tests on two long-input summarization datasets, GovReport (document) and QMSum (dialogue). Our model significantly outperforms the current state-of-the-art, including a 6.21 ROUGE-2 improvement on GovReport and a 2.13 ROUGE-1 improvement on QMSum. Further analysis shows that the dynamic weights make our generation process highly interpretable. Our code will be publicly available upon publication.

Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries

Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information. Thus, comparing the factual consistency of summaries is necessary as we develop improved models. However, the optimal human evaluation setup for factual consistency has not been standardized. To address this issue, we crowdsourced evaluations for factual consistency using the rating-based Likert scale and ranking-based Best-Worst Scaling protocols, on 100 articles from each of the CNN-Daily Mail and XSum datasets over four state-of-the-art models, to determine the most reliable evaluation framework. We find that ranking-based protocols offer a more reliable measure of summary quality across datasets, while the reliability of Likert ratings depends on the target dataset and the evaluation design. Our crowdsourcing templates and summary evaluations will be publicly available to facilitate future research on factual consistency in summarization.

FeTaQA: Free-form Table Question Answering

Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers. To address these issues and to demonstrate the full challenge of table question answering, we introduce FeTaQA, a new dataset with 10K Wikipedia-based {table, question, free-form answer, supporting table cells} pairs. FeTaQA yields a more challenging table question answering setting because it requires generating free-form text answers after retrieval, inference, and integration of multiple discontinuous facts from a structured knowledge source. Unlike datasets of generative QA over text in which answers are prevalent with copies of short text spans from the source, answers in our dataset are human-generated explanations involving entities and their high-level relations. We provide two benchmark methods for the proposed task: a pipeline method based on semantic-parsing-based QA systems and an end-to-end method based on large pretrained text generation models, and show that FeTaQA poses a challenge for both methods.