Fix Transformers backend FP8 MoE and remove some boilerplate (#46820)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-06-27 00:16:05 +01:00
committed by GitHub
parent 2ff76a5e85
commit d8eb734d94
29 changed files with 80 additions and 156 deletions
-1
View File
@@ -1114,7 +1114,6 @@ class Gemma4ForConditionalGeneration(
)
# --- MixtureOfExperts delegation to language_model ---
self.expert_weights = self.language_model.expert_weights
self.moe_layers = self.language_model.moe_layers
self.num_moe_layers = self.language_model.num_moe_layers
self.num_logical_experts = self.language_model.num_logical_experts