DBScholar

Back to papers

Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

Summary: Flash-LLM makes unstructured sparsity efficient on restrictive GPU tensor cores via “Load-as-Sparse, Compute-as-Dense,” targeting skinny, bandwidth-bound generative-model multiplications. It delivers up to 3.8× higher inference throughput and substantially lower cost on OPT-30B–175B. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
13631
Venue
VLDB
Year
2024
Pagerank
5.7099047e-05
Overall Rank
7,075 | 51.46%
DOI
10.14778/3626292.3626303

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{xia_vldb24,
        title = {{Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity}},
        author = {Xia, Haojun and Zheng, Zhen and Li, Yuchao and Zhuang, Donglin and Zhou, Zhongzhu and Qiu, Xiafei and Li, Yong and Lin, Wei and Song, Shuaiwen Leon},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {2},
        pages = {211--224},
        doi = {10.14778/3626292.3626303},
        url = {https://doi.org/10.14778/3626292.3626303},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank Citing Paper Year Venue Pagerank
6,900 Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving 2025 SIGMOD 5.7430032e-05
8,725 mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs 2025 VLDB 5.3766157e-05
10,769 Malleus: Straggler-Resilient Hybrid Parallel Training of Large-scale Models via Malleable Data and Model Parallelization 2025 SIGMOD 5.093636e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
420 Can Foundation Models Wrangle Your Data? 2023 VLDB 0.00018789852
521 PyTorch Distributed: Experiences on Accelerating Data Parallel Training 2020 VLDB 0.0001713368
1,793 TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data 2022 VLDB 9.7435472e-05
3,530 MiCS: Near-linear Scaling for Training Gigantic Model on Public Cloud 2023 VLDB 7.3379782e-05
3,782 CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Servers 2019 VLDB 7.1298979e-05
4,449 From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management 2022 VLDB 6.697553e-05
4,956 Heterogeneity-Aware Distributed Machine Learning Training via Partial Reduce 2021 SIGMOD 6.4290135e-05
5,003 Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism 2023 VLDB 6.4065691e-05
5,414 Optimizing Tensor Programs on Flexible Storage 2023 SIGMOD 6.2258658e-05
8,637 Harmony: Overcoming the Hurdles of GPU Memory Capacity to Train Massive DNN Models on Commodity Servers 2022 VLDB 5.3954887e-05
8,883 FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement 2023 SIGMOD 5.351513e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 7,240 Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search 2018 SIGMOD
2 10,410 TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware 2026 SIGMOD
3 10,259 KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference 2026 SIGMOD
4 8,883 FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement 2023 SIGMOD
5 10,856 Optimized Batch Prompting for Cost-effective LLMs 2025 VLDB
6 7,316 SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint 2025 SIGMOD
7 13,343 Database Perspective on LLM Inference Systems 2025 VLDB
8 10,219 DFLOP: A Data-driven Framework for Multimodal LLM Training Pipeline Optimization 2026 SIGMOD
9 6,432 RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference 2026 VLDB
10 9,880 MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training 2025 SIGMOD