Training a 4B model to produce 81% faster query plans than Postgres - Rohan Bansal
rohanbansal.com · 9,838 words · saved by 1 readers
...or how to make Qwen learn query optimization via agentic reinforcement learning
How good are query optimizers, really? Leis et al. asked this exact question in 2015. Then, they asked it again 10 years later. Despite an enormous body of research spanning a decade since their original exploration, they found that query optimizers continue to leave much to be desired. I was surprised when I first learned about this. A Postgres database should know everything about the stuff that lives in its tables, no? How hard can it be? As it turns out: enormously hard. In fact, one particular task a query optimizer needs to do, join ordering, is known to be NP-hard. So query…
saved by
related reading
- Training a 4B model to produce 81% faster query plans than Postgresrohanbansal.com
- Composer2.pdfcursor.com
- PostTrainBenchposttrainbench.com
- Putting Task Expertise into RL Achieves State-of-the-Art Performance on Text-to-SQLthinkingmachines.ai
- karl.pdfdatabricks.com
- Spending Inference Time - Kevin Lukevinlu.ai
- Open-Source Agentic Inference Benchmark | InferenceXinferencex.semianalysis.com
- Efficient LLM inferencefinbarrtimbers.substack.com
- RL Post-Training on Macs | Pluralis Researchpluralis.ai
- The lifecycle of a sharded Postgres query — PlanetScaleplanetscale.com
- Training an Agentic Router for Optimal Cost-Performance on SWE Tasks | Applied Computeappliedcompute.com
- Expert Data for Frontier AI - AfterQueryafterquery.com