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

31
vllm/model_executor/models/chatglm.py
View File

@@ -7,7 +7,6 @@
import json
from collections.abc import Iterable
from itertools import islice
from typing import Optional, Union
import torch
from torch import nn
@@ -50,8 +49,8 @@ class GLMAttention(nn.Module):
def __init__(
self,
config: ChatGLMConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -144,7 +143,7 @@ class GLMMLP(nn.Module):
def __init__(
self,
config: ChatGLMConfig,
quant_config: Optional[QuantizationConfig] = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -190,8 +189,8 @@ class GLMBlock(nn.Module):
def __init__(
self,
config: ChatGLMConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -263,8 +262,8 @@ class GLMTransformer(nn.Module):
def __init__(
self,
config: ChatGLMConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -295,7 +294,7 @@ class GLMTransformer(nn.Module):
self,
hidden_states: torch.Tensor,
position_ids: torch.Tensor,
) -> Union[torch.Tensor, IntermediateTensors]:
) -> torch.Tensor | IntermediateTensors:
for layer in islice(self.layers, self.start_layer, self.end_layer):
hidden_states = layer(
hidden_states=hidden_states, position_ids=position_ids
@@ -361,10 +360,10 @@ class ChatGLMModel(nn.Module, SupportsQuant):
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
intermediate_tensors: Optional[IntermediateTensors] = None,
inputs_embeds: Optional[torch.Tensor] = None,
intermediate_tensors: IntermediateTensors | None = None,
inputs_embeds: torch.Tensor | None = None,
**kwargs: object,
) -> Union[torch.Tensor, IntermediateTensors]:
) -> torch.Tensor | IntermediateTensors:
if get_pp_group().is_first_rank:
if inputs_embeds is not None:
hidden_states = inputs_embeds
@@ -459,7 +458,7 @@ class ChatGLMBaseModel(nn.Module):
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
@@ -491,9 +490,9 @@ class ChatGLMForCausalLM(ChatGLMBaseModel, SupportsLoRA, SupportsPP, SupportsQua
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.transformer(
input_ids, positions, intermediate_tensors, inputs_embeds
)