[Docs] Fix docstring continuation indentation in `routed_experts.py` (#53604)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Harry Mellor committed
Aug 24, 2026 at 19:27 UTC
b2dd9ce73dce2ad09007d1db5c171454118981d7
1 file changed
+6
-6
vllm/model_executor/layers/fused_moe/routed_experts.py
+6
-6
@@ -1040,13 +1040,13 @@ class RoutedExperts(PluggableLayer):
1040
num_experts: Number of logical (non-redundant) experts
1041
num_redundant_experts: Number of redundant experts
1042
lora_base_layer_prefix: LoRA ``base_layer.`` prefix for the
1043
- ``weight_name`` (checkpoint) side
1043
+ ``weight_name`` (checkpoint) side
1044
lora_base_layer_prefix_on_param_name: same, for the ``param_name``
1045
- side. Independent because ``get_expert_mapping`` resolves
1046
- ``param_name`` via ``getattr`` against this layer's bare
1047
- ``w13_weight``/``w2_weight`` (no prefix), while
1048
- ``make_expert_params_mapping`` indexes the model-wide
1049
- ``params_dict`` (prefix included).
1045
+ side. Independent because ``get_expert_mapping`` resolves
1046
+ ``param_name`` via ``getattr`` against this layer's bare
1047
+ ``w13_weight``/``w2_weight`` (no prefix), while
1048
+ ``make_expert_params_mapping`` indexes the model-wide
1049
+ ``params_dict`` (prefix included).
1050
include_fused: Prepend the fused pre-fused-checkpoint entries
1051
1052
Returns: