Files
FreeToken/python/freetoken/models
Xiaoze Fan 30dd715a93 fix(muse_glimmer)!: keep the attention gate out of the qkv fusion (#741)
The NVFP4 release quantizes the attention gate with a different weight global scale than q/k/v, so
one fused weight cannot carry a single global for all four parts.

BREAKING CHANGE: an FTW checkpoint converted with the fused qkvg_proj no longer loads; reconvert it
with `ft checkpoint`.
2026-10-18 23:16:37 -07:00
..