Menu

#Grpo

7 posts

Feed·
7 of 7 posts
Training a 4B model to produce 81% faster query plans than Postgres
📰
0Read More

Training a 4B model to produce 81% faster query plans than Postgres

Hacker News·2 months ago
#ut6JOjZ2
#rohanbansal#postgres#grpo#article#ama

...or how to make Qwen learn query optimization via agentic reinforcement learning

15s