TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware
Summary: TranSQL+ compiles LLM computation graphs into pure SQL to run inference inside relational DBs, leveraging vectorized execution and out‑of‑core processing to avoid GPUs or external runtimes. Introduces ROW2COL for matrix joins and gets up to 20× lower prefill latency and 4× faster decoding on low‑memory, CPU‑only hardware. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Wenbo Sun (Delft University of Technology)
- 2. Qiming Guo (Texas A&M University - Corpus Christi)
- 3. Wenlu Wang (Texas A&M University - Corpus Christi)
- 4. Rihan Hai (Delft University of Technology)
BibTeX Citation
@inproceedings{sun_sigmod26,
title = {{TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware}},
author = {Sun, Wenbo and Guo, Qiming and Wang, Wenlu and Hai, Rihan},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769836},
url = {https://dl.acm.org/doi/10.1145/3769836},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 103 | DuckDB: an Embeddable Analytical Database | 2019 | SIGMOD | 0.00034161428 |
| 1,235 | Towards Linear Algebra over Normalized Data | 2017 | VLDB | 0.00011548457 |
| 2,179 | Enabling and Optimizing Non-linear Feature Interactions in Factorized Linear Algebra | 2019 | SIGMOD | 9.0146333e-05 |
| 2,347 | Vertica-ML: Distributed Machine Learning in Vertica Database | 2020 | SIGMOD | 8.7157552e-05 |
| 2,370 | Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning | 2019 | VLDB | 8.6795925e-05 |
| 3,653 | ClickHouse - Lightning Fast Analytics for Everyone | 2024 | VLDB | 7.2241143e-05 |
| 6,046 | Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra | 2021 | SIGMOD | 5.9956597e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,305 | The Power of Constraints in Natural Language to SQL Translation | 2025 | VLDB |
| 2 | 7,809 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD |
| 3 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 4 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |
| 5 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 6 | 10,732 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 7 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 8 | 4,045 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 9 | 13,343 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 10 | 9,542 | Database as Runtime: Compiling LLMs to SQL for In-database Model Serving | 2025 | SIGMOD |