mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-22 00:23:05 +08:00
* feat(qwen3_5_moe): read every checkpoint layout through the QuantConfig NVFP4 dense layers now declare the input_scale their scheme carries, so an FTW written by an older build from an NVFP4 dense checkpoint needs scripts/ftw_hotfix.py before it loads again. * fix(quant): address scheme reader review: hotfix dialect names, gemma4 cross-shard scales, ct block-fp8 experts