[MyPy] Fix mypy for vllm/lora (#41722)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
This commit is contained in:
Martin Hickey
2026-06-22 10:57:09 -04:00
committed by GitHub
parent 1c7bc18318
commit ccd49f6821
15 changed files with 140 additions and 50 deletions
+14 -3
View File
@@ -33,7 +33,7 @@ def _mcp_apply(x, bias, layer: "ColumnParallelLinearWithLoRA"):
== len(layer.output_slices)
)
output = layer.base_layer.quant_method.apply(layer.base_layer, x, bias)
output = layer._get_quant_method().apply(layer.base_layer, x, bias)
x = x.view(-1, x.shape[-1])
output, out_orig_shape = output.view(-1, output.shape[-1]), output.shape
@@ -73,6 +73,8 @@ def _mcp_apply(x, bias, layer: "ColumnParallelLinearWithLoRA"):
)
if not current_platform.can_update_inplace():
if lora_output is None:
raise RuntimeError("LoRA expand must return an output tensor.")
output = lora_output
output = output.view(*out_orig_shape)
@@ -327,12 +329,16 @@ class MergedColumnParallelLinearWithLoRA(ColumnParallelLinearWithLoRA):
def apply(self, x: torch.Tensor, bias: torch.Tensor | None = None) -> torch.Tensor:
merged_cls = maybe_get_oot_by_class(MergedColumnParallelLinear)
base_forward = getattr(type(self.base_layer), "forward", None)
merged_forward = getattr(merged_cls, "forward", None)
# Effectively unsharded subclasses can safely reuse their custom
# forward() implementation before applying the LoRA delta.
if (
self.tp_size == 1
and type(self.base_layer) is not merged_cls
and type(self.base_layer).forward is not merged_cls.forward
and base_forward is not None
and merged_forward is not None
and base_forward is not merged_forward
):
return self._apply_base_forward(x)
return _mcp_apply(x, bias, self)
@@ -482,6 +488,7 @@ class MergedQKVParallelLinearWithLoRA(MergedColumnParallelLinearWithLoRA):
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
decorate: bool = True,
) -> bool:
return (
type(source_layer) is maybe_get_oot_by_class(QKVParallelLinear)
@@ -523,6 +530,7 @@ class ColumnParallelLinearWithShardedLoRA(ColumnParallelLinearWithLoRA):
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
decorate: bool = True,
) -> bool:
# specifying kwargs so they can be easily accessed in decorator
return super().can_replace_layer(
@@ -565,6 +573,7 @@ class MergedColumnParallelLinearWithShardedLoRA(MergedColumnParallelLinearWithLo
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
decorate: bool = True,
) -> bool:
# specifying kwargs so they can be easily accessed in decorator
return super().can_replace_layer(
@@ -650,6 +659,7 @@ class MergedQKVParallelLinearWithShardedLoRA(MergedQKVParallelLinearWithLoRA):
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
decorate: bool = True,
) -> bool:
# specifying kwargs so they can be easily accessed in decorator
return super().can_replace_layer(
@@ -678,6 +688,7 @@ class MergedColumnParallelLinearVariableSliceWithLoRA(
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
decorate: bool = True,
) -> bool:
# Support MergedColumnParallelLinear with 3 or more slices
# (2 slices are handled by MergedColumnParallelLinearWithLoRA)
@@ -727,7 +738,7 @@ class MergedColumnParallelLinearVariableSliceWithLoRA(
start_idx = 0
for output_size in output_sizes:
end_idx = start_idx + output_size
lora_b_list.append(lora_b[start_idx:end_idx, :])
lora_b_list.append(lora_b[start_idx:end_idx])
start_idx = end_idx
lora_b = lora_b_list