[Model] Drop the 4x M-RoPE cache headroom for Qwen3-VL, Qwen3.5 and Qwen3.8 (#59853)
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com> Signed-off-by: lesj0610 <lesj0610@gmail.com> Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
This commit is contained in:
@@ -508,6 +508,10 @@ class ModelConfig:
|
||||
# here early.
|
||||
if self.multimodal_config:
|
||||
factors["language_model_only"] = self.multimodal_config.language_model_only
|
||||
# Sizes Qwen3.5's M-RoPE cache.
|
||||
factors["video_pruning"] = (
|
||||
self.multimodal_config.is_multimodal_pruning_enabled()
|
||||
)
|
||||
return hash_factors(factors)
|
||||
|
||||
def _update_nested(
|
||||
|
||||
Reference in New Issue
Block a user