fix(fp8): never apply FP8 storage to already-quantized weights - #9416

Merged

lstein merged 22 commits into

invoke-ai:mainfrom

Pfannkuchensack:feat/fp8_quantized_guard

Aug 25, 2026

Commits on Jul 31, 2026

Commits on Aug 2, 2026

Merge branch 'main' into feat/fp8_quantized_guard
Pfannkuchensack
authored
8826e8d
Merge branch 'main' into feat/fp8_anima
Pfannkuchensack
authored
ec0b1f3
Merge branch 'main' into feat/fp8_zimage
Pfannkuchensack
authored
8734f29

Commits on Aug 6, 2026

Merge branch 'main' into feat/fp8_zimage
Pfannkuchensack
authored
6b52aec
Merge branch 'main' into feat/fp8_anima
Pfannkuchensack
authored
6c38314
Merge branch 'main' into feat/fp8_quantized_guard
Pfannkuchensack
authored
5d81932

Commits on Aug 14, 2026

Commits on Aug 17, 2026

Commits on Aug 24, 2026

Merge branch 'main' into feat/fp8_quantized_guard
Pfannkuchensack
authored
d8b9841

Commits on Aug 25, 2026

Merge commit 'refs/tmp/main' into pr9416-work
lstein
committed
a9e3c29
fix(fp8): add sdnq_quantized to the quantized-format guard

lstein
and
claude
committed
b187ae4