wevads-gpu/README.md

WEVADS GPU Server

• IP: managed outside this repository
• GPU: NVIDIA RTX 4000 SFF Ada (20GB vRAM)
• RAM: 62GB DDR4
• Disk: 1.7TB NVMe
• Ollama: localhost:11434
• Legacy local models: deepseek-r1:8b, deepseek-r1:32b, llama3.1:8b

Ops scripts in this repo

• nonreg-framework.sh: anti-regression gate (HTTP/API/WEVIA/tracking/confidentiality checks)
• multiinstall-safe-preflight.sh: safe server preflight before multi-install batches
• execute_all_p0_p1_p2.sh: full execution pipeline (P0/P1/P2) with Sentinel checks and final report
• dp-release-gate.sh: guardrail checks (forbidden touches, confidentiality, php-lint, cleanliness)
• CHANTIERS_RESTANTS_EXECUTION_PLAN.md: execution plan and GO/NO-GO criteria
• REGLES_EXECUTION_OBLIGATOIRES.md: mandatory execution policy agreed with DP