Centralizes GPU device selection, capability detection, and per-model batch size optimization to replace hardcoded RTX 3050 Ti limits. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Centralizes GPU device selection, capability detection, and per-model batch size optimization to replace hardcoded RTX 3050 Ti limits. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>