Danyang Zhuo

Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support

Alexander Du, Jianjun Ou, Danyang Zhuo, Matthew Lentz

Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static errors are costly in both latency and token consumption. Post-hoc repair …

Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support

Alexander Du, Jianjun Ou, Danyang Zhuo, Matthew Lentz

Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static errors are costly in both latency and token consumption. Post-hoc repair …

us (code pays fourni par la source)

Curator: Efficient Vector Search with Low-Selectivity Filters

Yicheng Jin, Wenjun Hu, Bruce MacDowell Maggs, Xiao Zhang et autres

Embedding-based dense retrieval has become the cornerstone of many critical applications, where approximate nearest neighbor search (ANNS) queries are often combined with filters on labels such as dates and price ranges. Graph-based indexes achieve state-of-the-art performance on unfiltered ANNS but encounter connectivity …

us (code pays fourni par la source)

Curator: Efficient Vector Search with Low-Selectivity Filters

Yicheng Jin, Yongji Wu, Wenjun Hu, Bruce MacDowell Maggs et autres

Embedding-based dense retrieval has become the cornerstone of many critical applications, where approximate nearest neighbor search (ANNS) queries are often combined with filters on labels such as dates and price ranges. Graph-based indexes achieve state-of-the-art performance on unfiltered ANNS but encounter connectivity …

Curator: Efficient Vector Search with Low-Selectivity Filters

Yicheng Jin, Yongji Wu, Wenjun Hu, Bruce MacDowell Maggs et autres

Embedding-based dense retrieval has become the cornerstone of many critical applications, where approximate nearest neighbor search (ANNS) queries are often combined with filters on labels such as dates and price ranges. Graph-based indexes achieve state-of-the-art performance on unfiltered ANNS but encounter connectivity …

DecodeX: Exploring and Benchmarking of LDPC Decoding across CPU, GPU, and ASIC Platforms

Zhenzhou Qi, Yiming Li, Chung-Hsuan Tung, Danyang Zhuo et autres

Emerging virtualized radio access networks (vRANs) demand flexible and efficient baseband processing across heterogeneous compute substrates. In this paper, we present DecodeX, a unified benchmarking framework for evaluating low-density parity-check (LDPC) decoding acceleration across different hardware platforms. DecodeX integrates a comprehensive suite …

LLM.265: Video Codecs Are Secretly Tensor Codecs

Ceyu Xu, Yongji Wu, X.D. Yang, Beidi Chen et autres

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs.To mitigate these bottlenecks, various tensor compression techniques have …

us, hk (code pays fourni par la source)

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models

Yixiao Wang, Qinsi Wang, Ting Xin Jiang, Zhixu Du et autres

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal accuracy loss. Previous SVD-based approaches have focused …

AXLearn: Modular, Hardware-Agnostic Large Model Training

Mark Lee, Chang Lan, Tom Gunter, John Peebles et autres

AXLearn is a production system which facilitates scalable and high-performance training of large deep learning models. Compared to other state-of-art deep learning systems, AXLearn has a unique focus on modularity and support for hardware-agnostic training. AXLearn's internal interfaces between software components follow …

Can Large Language Models Verify System Software? A Case Study Using FSCQ as a Benchmark

Jianxing Qin, Alexander Du, Danfeng Zhang, Matthew Lentz et autres

Large language models (LLMs) have demonstrated remarkable coding capabilities. They excel in code synthesis benchmarks across diverse domains and have become ubiquitous in coding tools. Recently, they have also shown promise in generating mathematical proofs and small software programs. In this paper, …

us (code pays fourni par la source)

Rethinking RPC Communication for Microservices-based Applications

Xiangfeng Zhu, Yang Zhou, Yuyao Wang, Xiangyu Gao et autres

Fast and efficient RPCs are key to the performance of applications based on microservices. But RPC communication suffers from significant overhead today because it relies on the standard, layered protocol stack and loose coupling between the end host and in-network proxies that …

us (code pays fourni par la source)

Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation

Jingrong Chen, Yongji Wu, Liang Luo, Zhaodong Wang et autres

Modern machine learning (ML) training workloads place substantial demands on both computational and communication resources. Consequently, accurate performance estimation has become increasingly critical for guiding system design decisions, such as the selection of parallelization strategies, cluster configurations, and hardware provisioning. Existing simulation-based …