Document all published assets and corrected inference profiles

README.md

@@ -23,3 +23,9 @@ Use the GitHub current guide and requirements-paper512.txt, obtain separately au
 Use source commit https://github.com/CurMack/markermogen/tree/330ce8bdc124bd4df6a9acf714872087785fac05 and the matching `global_development_cpu_geometry_profile.json` next to each model. Triangulation uses identical CPU equations for all inputs; root/shape fitting, diffusion and guidance run on GPU. All 56 geometry checks were bitwise equal to the original CPU equations, and CUDA validation now runs. This is a runtime correction; quality remains experimental. Initial profiles and their source commit are retained for reproducibility.
 
 ViTPose, SAM3DBody and MHR are available with their licenses and exact official revisions in assets.json and official_sources.json. MammaNet and SMPL/SMPL-X require official authorized downloads.
+
+## Repaired CUDA inference source
+
+Use source commit https://github.com/CurMack/markermogen/tree/330ce8bdc124bd4df6a9acf714872087785fac05 and the matching `global_development_cpu_geometry_profile.json` next to each model. Triangulation uses identical CPU equations for all inputs; root/shape fitting, diffusion and guidance run on GPU. All 56 geometry checks were bitwise equal to the original CPU equations, and CUDA validation now runs. This is a runtime correction; quality remains experimental. Initial profiles and their source commit are retained for reproducibility.
+
+ViTPose, SAM3DBody and MHR are available with their licenses and exact official revisions in assets.json and official_sources.json. MammaNet and SMPL/SMPL-X require official authorized downloads.