biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-12 17:51:31 +01:00
committed by GitHub
parent 9bb38130cb
commit 8fcaaf6a16
944 changed files with 9490 additions and 10121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
vllm/model_executor/models/bailing_moe.py
View File

@@ -26,7 +26,6 @@
from collections.abc import Iterable
from itertools import islice
from typing import Optional, Union
import torch
import torch.nn.functional as F
@@ -75,8 +74,8 @@ class BailingAttention(nn.Module):
def __init__(
self,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
reduce_results: bool = True,
prefix: str = "",
):
@@ -184,8 +183,8 @@ class BailingMLP(nn.Module):
self,
intermediate_size: int,
config: PretrainedConfig,
quant_config: Optional[QuantizationConfig] = None,
reduce_results: Optional[bool] = True,
quant_config: QuantizationConfig | None = None,
reduce_results: bool | None = True,
prefix: str = "",
) -> None:
super().__init__()
@@ -218,8 +217,8 @@ class BailingMoE(nn.Module):
self,
intermediate_size: int,
config: PretrainedConfig,
quant_config: Optional[QuantizationConfig] = None,
reduce_results: Optional[bool] = True,
quant_config: QuantizationConfig | None = None,
reduce_results: bool | None = True,
prefix: str = "",
):
super().__init__()
@@ -340,8 +339,8 @@ class BailingMoeBlock(nn.Module):
def __init__(
self,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -370,7 +369,7 @@ class BailingMoeBlock(nn.Module):
self,
hidden_states: torch.Tensor,
position_ids: torch.Tensor,
residual: Optional[torch.Tensor],
residual: torch.Tensor | None,
) -> torch.Tensor:
if residual is None:
residual = hidden_states
@@ -447,9 +446,9 @@ class BailingMoeModel(nn.Module):
self,
input_ids: torch.Tensor,
position_ids: torch.Tensor,
intermediate_tensors: Optional[IntermediateTensors],
inputs_embeds: Optional[torch.Tensor] = None,
) -> Union[torch.Tensor, IntermediateTensors]:
intermediate_tensors: IntermediateTensors | None,
inputs_embeds: torch.Tensor | None = None,
) -> torch.Tensor | IntermediateTensors:
if get_pp_group().is_first_rank:
if inputs_embeds is not None:
hidden_states = inputs_embeds
@@ -619,9 +618,9 @@ class BailingMoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
intermediate_tensors: Optional[IntermediateTensors] = None,
inputs_embeds: Optional[torch.Tensor] = None,
) -> Union[torch.Tensor, IntermediateTensors]:
intermediate_tensors: IntermediateTensors | None = None,
inputs_embeds: torch.Tensor | None = None,
) -> torch.Tensor | IntermediateTensors:
model_output = self.model(
input_ids, positions, intermediate_tensors, inputs_embeds
)
@@ -630,7 +629,7 @@ class BailingMoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
def compute_logits(
self,
hidden_states: torch.Tensor,
) -> Optional[torch.Tensor]:
) -> torch.Tensor | None:
logits = self.logits_processor(self.lm_head, hidden_states)
return logits