Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated)

youtu_llm_2b_decode_absorbed_msdpa: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py

Card: DeviceMark row (2026-09)

Card metadata: library_name coreai, ensure coreai tag

Card: definition line (Core AI, 2026-09)

Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)

Link the card back to its collection and the request box

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle

Note b2 (beta3-loadable) bundles under gpu-pipelined-b2/

Add b2 (beta3-loadable) bundle under gpu-pipelined-b2/youtu_llm_2b_decode_absorbed_int8_msdpa_g32/ (b1 retained)

Card: lead with CoreAIKit ChatSession (kit-enrolled)

Add source config.json

Add model card

Add Youtu-LLM-2B int8 pipelined-decode bundle (absorbed MLA)

initial commit