John Pollock 429be7c912 docs: update activeContext for v2.5.0 release with refactoring summary ...

Update active context documentation to reflect v2.5.0 release candidate status.
Major achievements documented:

- DisTorch2 allocation refactoring (-179 lines, unified UNET/CLIP logic)
- Production cleanup removing debug instrumentation (-40 lines)
- Verified selective unload system working with production logs
- Architecture status showing all core files production-ready
- Updated memory management pipeline with verification details

Reorganized content to prioritize recent session achievements (2025-09-30)
and production readiness status. Total code reduction: 219 lines through
consolidation and cleanup while maintaining full functionality.

2025-09-30 09:07:05 -05:00

..

reference-logs

an interesting experiment that produces wrong behavior but no OOM. Looks like we are circling it and I don't want to lose this intermediate step.

2025-09-28 12:15:52 -05:00

activeContext.md

docs: update activeContext for v2.5.0 release with refactoring summary

2025-09-30 09:07:05 -05:00

code-references.md

docs(memory-bank): sync with current code state for selective ejection\n\n- Document Phase 3 implemented without global sentinel (_mgpu_unload_distorch_model per-model flag)\n- Describe patched unload_all_models selective behavior and current all-kept delegation caveat\n- Outline rediscovery plan and strict no-op target when no models are flagged\n- Update active context, system patterns, code references, progress, tech context, and lineage

2025-09-29 07:57:35 -05:00

comfy_core.py

commiting this steaming pile of hot garbage for future dissection to see if I want any organs from this terminally ill branch

2025-09-25 14:36:13 -05:00

comfyui-lineage.md

docs(memory-bank): sync with current code state for selective ejection\n\n- Document Phase 3 implemented without global sentinel (_mgpu_unload_distorch_model per-model flag)\n- Describe patched unload_all_models selective behavior and current all-kept delegation caveat\n- Outline rediscovery plan and strict no-op target when no models are flagged\n- Update active context, system patterns, code references, progress, tech context, and lineage

2025-09-29 07:57:35 -05:00

performance-benchmarks.md

docs: add development rules and project context in .clinerules

2025-09-23 20:58:03 -05:00

productContext.md

docs: add development rules and project context in .clinerules

2025-09-23 20:58:03 -05:00

progress.md

docs: update activeContext for v2.5.0 release with refactoring summary

2025-09-30 09:07:05 -05:00

projectbrief.md

docs: add development rules and project context in .clinerules

2025-09-23 20:58:03 -05:00

systemPatterns.md

docs: update activeContext for v2.5.0 release with refactoring summary

2025-09-30 09:07:05 -05:00

techContext.md

docs(memory-bank): sync with current code state for selective ejection\n\n- Document Phase 3 implemented without global sentinel (_mgpu_unload_distorch_model per-model flag)\n- Describe patched unload_all_models selective behavior and current all-kept delegation caveat\n- Outline rediscovery plan and strict no-op target when no models are flagged\n- Update active context, system patterns, code references, progress, tech context, and lineage

2025-09-29 07:57:35 -05:00