Alay Dilipbhai Shah

Dimitris Stripelis, Zijian Hu, Jipeng Zhang et al.

With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present TO-Router, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query's requirements. Through extensive experiments, we demonstrate that when compared to standalone expert models, TO-Router improves query efficiency by up to 40\%, and leads to significant cost reductions of up to 30%, while maintaining or enhancing model performance by up to 10%.

Yuhang Yao, Han Jin, Alay Dilipbhai Shah et al.

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Zijian Hu, Jipeng Zhang, Rui Pan et al.

We present Fox-1, a series of small language models (SLMs) consisting of Fox-1-1.6B and Fox-1-1.6B-Instruct-v0.1. These models are pre-trained on 3 trillion tokens of web-scraped document data and fine-tuned with 5 billion tokens of instruction-following and multi-turn conversation data. Aiming to improve the pre-training efficiency, Fox-1-1.6B model introduces a novel 3-stage data curriculum across all the training data with 2K-8K sequence length. In architecture design, Fox-1 features a deeper layer structure, an expanded vocabulary, and utilizes Grouped Query Attention (GQA), offering a performant and efficient architecture compared to other SLMs. Fox-1 achieves better or on-par performance in various benchmarks compared to StableLM-2-1.6B, Gemma-2B, Qwen1.5-1.8B, and OpenELM1.1B, with competitive inference speed and throughput. The model weights have been released under the Apache 2.0 license, where we aim to promote the democratization of LLMs and make them fully accessible to the whole open-source community.

Haojun Xia, Xiaoxia Wu, Jisen Li et al.

The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for mixed-precision KV caching: Kitty. On the algorithm side, extensive experiments show that Dynamic Channel-wise Precision Boost -- which ranks Key-cache channels by sensitivity and keeps only a small fraction at higher precision -- maintains near-zero loss in accuracy drop while approaching 2-bit memory. The main challenge is handling dynamic 4-bit channel boosts while keeping the page layout coalesced and the dequantization uniform, with no scattered reads or hard-coded masks. Kitty addresses these issues by decompose each mixed-precision Key page into two tensors with unified 2-bit precision. Based on this, Kitty provides a page-centric KV layout, Triton-compatible page dequantization kernels, and a lightweight runtime pipeline that preserves coalescing and avoids divergence. Across seven tasks and two model families (Qwen3, LLaMA3), Kitty cuts KV memory by nearly 8x with negligible accuracy loss, enabling up to 8x larger batches and 2.1x-4.1x higher throughput under the same memory budget. We release the full implementation of Kitty at https://github.com/Summer-Summer/Kitty.

Chaoyang He, Alay Dilipbhai Shah, Zhenheng Tang et al.

Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized training due to the lack of exploration in diverse tasks with a unified FL framework. FL has rarely been demonstrated effectively in advanced computer vision tasks such as object detection and image segmentation. To bridge the gap and facilitate the development of FL for computer vision tasks, in this work, we propose a federated learning library and benchmarking framework, named FedCV, to evaluate FL on the three most representative computer vision tasks: image classification, image segmentation, and object detection. We provide non-I.I.D. benchmarking datasets, models, and various reference FL algorithms. Our benchmark study suggests that there are multiple challenges that deserve future exploration: centralized training tricks may not be directly applied to FL; the non-I.I.D. dataset actually downgrades the model accuracy to some degree in different tasks; improving the system efficiency of federated training is challenging given the huge number of parameters and the per-client memory cost. We believe that such a library and benchmark, along with comparable evaluation settings, is necessary to make meaningful progress in FL on computer vision tasks. FedCV is publicly available: https://github.com/FedML-AI/FedCV.

Yide Ran, Zhaozhuo Xu, Yuhang Yao et al.

The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external API functions to enhance their performance. However, challenges such as data scarcity, ineffective question formatting, and catastrophic forgetting hinder the development of on-device LLM agents. To tackle these issues, we propose Alopex, a framework that enables precise on-device function calls using the Fox LLM. Alopex introduces a logic-based method for generating high-quality training data and a novel ``description-question-output'' format for fine-tuning, reducing risks of function information leakage. Additionally, a data mixing strategy is used to mitigate catastrophic forgetting, combining function call data with textbook datasets to enhance performance in various tasks. Experimental results show that Alopex improves function call accuracy and significantly reduces catastrophic forgetting, providing a robust solution for integrating function call capabilities into LLMs without manual intervention.

Shanshan Han, Zijian Hu, Alay Dilipbhai Shah et al.

We introduce TorchOpera, a compound AI system for enhancing the safety and quality of prompts and responses for Large Language Models. TorchOpera ensures that all user prompts are safe, contextually grounded, and effectively processed, while enhancing LLM responses to be relevant and high quality. TorchOpera utilizes the vector database for contextual grounding, rule-based wrappers for flexible modifications, and specialized mechanisms for detecting and adjusting unsafe or incorrect content. We also provide a view of the compound AI system to reduce the computational cost. Extensive experiments show that TorchOpera ensures the safety, reliability, and applicability of LLMs in real-world settings while maintaining the efficiency of LLM responses.

Devendra Swami, Alay Dilipbhai Shah, Subhrajeet K B Ray

Techniques for making future predictions based upon the present and past data, has always been an area with direct application to various real life problems. We are discussing a similar problem in this paper. The problem statement is provided by Kaggle, which also serves as an ongoing competition on the Kaggle platform. In this project, we worked with a challenging time-series dataset consisting of daily sales data, kindly provided by one of the largest Russian software firms - 1C Company. The objective is to predict the total sales for every product and store in the next month given the past data. In order to perform forecasting for next month, we have deployed eXtreme Gradient Boosting (XGBoost) and Long Short Term Memory (LSTM) based network architecture to perform learning task. Root mean squared error (RMSE) between the actual and predicted target values is used to evaluate the performance, and make comparisons between the deployed algorithms. It has been found that XGBoost fared better than LSTM over this dataset which can be attributed to its relatively higher sparsity.