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

27
vllm/model_executor/models/longcat_flash.py
View File

@@ -36,7 +36,6 @@
import typing
from collections.abc import Callable, Iterable
from itertools import islice
from typing import Optional, Union
import torch
from torch import nn
@@ -194,7 +193,7 @@ class FlashMLP(nn.Module):
hidden_size: int,
intermediate_size: int,
hidden_act: str,
quant_config: Optional[QuantizationConfig] = None,
quant_config: QuantizationConfig | None = None,
reduce_results: bool = True,
prefix: str = "",
) -> None:
@@ -270,8 +269,8 @@ class LongcatMoe(nn.Module):
top_k: int,
hidden_size: int,
intermediate_size: int,
params_dtype: Optional[torch.dtype] = None,
quant_config: Optional[QuantizationConfig] = None,
params_dtype: torch.dtype | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
enable_eplb: bool = False,
):
@@ -329,8 +328,8 @@ class FlashDecoderLayer(nn.Module):
self,
vllm_config: VllmConfig,
config: FlashConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
enable_eplb: bool = False,
) -> None:
@@ -415,7 +414,7 @@ class FlashDecoderLayer(nn.Module):
self,
positions: torch.Tensor,
hidden_states: torch.Tensor,
residual: Optional[torch.Tensor],
residual: torch.Tensor | None,
) -> tuple[torch.Tensor, torch.Tensor]:
if residual is None:
residual = hidden_states
@@ -506,9 +505,9 @@ class FlashModel(nn.Module):
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:
if get_pp_group().is_first_rank:
if inputs_embeds is not None:
hidden_states = inputs_embeds
@@ -592,9 +591,9 @@ class LongcatFlashForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
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:
hidden_states = self.model(
input_ids, positions, intermediate_tensors, inputs_embeds
)
@@ -603,7 +602,7 @@ class LongcatFlashForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
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