CLAUDE: add run_infer_local.sh — local GPU infer_server (no DGX/docker/transfer)

Run the PyTorch L1+L2 server on the workstation 5060 Ti; Java pipeline points at 127.0.0.1:5577.
Verified: server loads L1(weighted9_pm_s)+L2(l2_v1) on CUDA, warm-up + pyramid build OK.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>