⚡ Optimize /solve endpoint concurrency by offloading ML inference to background threads#4

Open

dhanush342 wants to merge 1 commit intomainfrom

perf/asyncio-threadpool-inference-15587154736274272447

Commits on Mar 18, 2026

perf: use asyncio.to_thread for ML inference to prevent blocking the event loop

google-labs-jules[bot]
and
dhanush342
committed