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

23
vllm/model_executor/models/persimmon.py
View File

@@ -25,7 +25,6 @@
from collections.abc import Iterable
from itertools import islice
from typing import Optional, Union
import torch
from torch import nn
@@ -63,7 +62,7 @@ from .utils import (
class PersimmonMLP(nn.Module):
def __init__(
self, config: PersimmonConfig, quant_config: Optional[QuantizationConfig] = None
self, config: PersimmonConfig, quant_config: QuantizationConfig | None = None
):
super().__init__()
self.dense_h_to_4h = ColumnParallelLinear(
@@ -85,8 +84,8 @@ class PersimmonAttention(nn.Module):
def __init__(
self,
config: PersimmonConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -181,8 +180,8 @@ class PersimmonDecoderLayer(nn.Module):
def __init__(
self,
config: PersimmonConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -263,9 +262,9 @@ class PersimmonModel(nn.Module):
self,
input_ids: torch.Tensor,
positions: 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
@@ -340,8 +339,8 @@ class PersimmonForCausalLM(nn.Module, SupportsPP):
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,
):
hidden_states = self.model(
input_ids=input_ids,
@@ -354,7 +353,7 @@ class PersimmonForCausalLM(nn.Module, 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