Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-12 09:51:31 -07:00
committed by GitHub
parent 9bb38130cb
commit 8fcaaf6a16
944 changed files with 9490 additions and 10121 deletions
+6 -9
View File
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from typing import Optional, Union
import torch
import torch.nn as nn
@@ -41,7 +40,7 @@ class RowParallelLinearWithLoRA(BaseLinearLayerWithLoRA):
def forward(
self, input_: torch.Tensor
) -> Union[torch.Tensor, tuple[torch.Tensor, Optional[torch.Tensor]]]:
) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor | None]:
"""Forward of RowParallelLinear
Args:
@@ -93,7 +92,7 @@ class RowParallelLinearWithLoRA(BaseLinearLayerWithLoRA):
source_layer: nn.Module,
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: Optional[PretrainedConfig],
model_config: PretrainedConfig | None,
) -> bool:
return type(source_layer) is RowParallelLinear
@@ -120,9 +119,7 @@ class RowParallelLinearWithShardedLoRA(RowParallelLinearWithLoRA):
lora_b = lora_b[start_idx:end_idx, :]
return lora_b
def apply(
self, x: torch.Tensor, bias: Optional[torch.Tensor] = None
) -> torch.Tensor:
def apply(self, x: torch.Tensor, bias: torch.Tensor | None = None) -> torch.Tensor:
output = self.base_layer.quant_method.apply(self.base_layer, x)
x = x.view(-1, x.shape[-1])
@@ -133,7 +130,7 @@ class RowParallelLinearWithShardedLoRA(RowParallelLinearWithLoRA):
device=x.device,
)
shrunk_buffer: Optional[torch.Tensor] = self.punica_wrapper.add_shrink(
shrunk_buffer: torch.Tensor | None = self.punica_wrapper.add_shrink(
buffer, x, self.lora_a_stacked, 1.0
)
if not current_platform.can_update_inplace():
@@ -150,7 +147,7 @@ class RowParallelLinearWithShardedLoRA(RowParallelLinearWithLoRA):
# NOTE offset are based on the rank.
shard_size = self.lora_b_stacked[0].shape[2]
offset_start = self.tp_rank * shard_size
lora_output: Optional[torch.Tensor] = self.punica_wrapper.add_expand(
lora_output: torch.Tensor | None = self.punica_wrapper.add_expand(
output,
buffer,
self.lora_b_stacked,
@@ -172,7 +169,7 @@ class RowParallelLinearWithShardedLoRA(RowParallelLinearWithLoRA):
source_layer: nn.Module,
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: Optional[PretrainedConfig],
model_config: PretrainedConfig | None,
) -> bool:
# specifying kwargs so they can be easily accessed in decorator
return super().can_replace_layer(