Files
serverAppConfigs/tests
Frank bab8f7f839 frank-small: revert to bf16 KV — the only dtype that boots Gemma4
int8_per_token_head: page-size unification fails (scale tensor breaks
the 256/512 head-dim ratio). turboquant_k8v4: backend validation fails
(no mm-prefix attention, which Gemma4's vision/audio path requires).
fp8: hardware-dead on sm_86. bf16 it is; history documented in
frank-small.env, seam pins auto + no backend pin.
2026-09-19 00:26:11 -07:00
..