Database Paper Browser

Back to papers

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)

Paper ID
7432
Venue
SIGMOD
Year
2026
Pagerank
4.1945683e-05
Overall Rank
10,122 | 29.59%
DOI
10.1145/3769836

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

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.

Previous Page 1 / 1 Next

Semantically Similar Papers