[Bugfix] DiffusionGemma: fix multimodal support (#57589)
Signed-off-by: Matt Mastracci <matthew@mastracci.com> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Claude Fable 5.1
Lucas Wilkinson
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
9a70c233cd
commit
ff0c885494
@@ -197,6 +197,11 @@ class DiffusionGemmaForConditionalGeneration(
|
||||
text_config.attention_k_eq_v = True
|
||||
|
||||
# ---- Vision tower ----
|
||||
# Gemma4's image path, borrowed below, reads this flag.
|
||||
lora_config = vllm_config.lora_config
|
||||
self._enable_mm_lora = bool(
|
||||
lora_config is not None and lora_config.enable_tower_connector_lora
|
||||
)
|
||||
vision_config = getattr(config, "vision_config", None)
|
||||
self.embed_vision: Gemma4MultimodalEmbedder | None
|
||||
if vision_config is not None:
|
||||
|
||||
Reference in New Issue
Block a user