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

36
vllm/model_executor/models/lfm2.py
View File

@@ -2,7 +2,7 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Iterable
from itertools import islice
from typing import Any, Optional
from typing import Any
import torch
import torch.nn as nn
@@ -54,8 +54,8 @@ class Lfm2MLP(nn.Module):
ff_dim: int,
multiple_of: int,
auto_adjust_ff_dim: bool,
ffn_dim_multiplier: Optional[float],
quant_config: Optional[QuantizationConfig] = None,
ffn_dim_multiplier: float | None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
):
super().__init__()
@@ -98,10 +98,10 @@ class Lfm2Attention(nn.Module):
num_heads: int,
num_kv_heads: int,
rope_theta: float = 10000,
rope_scaling: Optional[dict[str, Any]] = None,
rope_scaling: dict[str, Any] | None = None,
max_position_embeddings: int = 8192,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
) -> None:
super().__init__()
@@ -190,9 +190,9 @@ class Lfm2AttentionDecoderLayer(nn.Module):
self,
config: Lfm2Config,
layer_idx: int,
model_config: Optional[ModelConfig] = None,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
model_config: ModelConfig | None = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
) -> None:
super().__init__()
@@ -240,7 +240,7 @@ class Lfm2AttentionDecoderLayer(nn.Module):
self,
positions: torch.Tensor,
hidden_states: torch.Tensor,
residual: Optional[torch.Tensor],
residual: torch.Tensor | None,
**kwargs,
) -> tuple[torch.Tensor, torch.Tensor]:
if residual is None:
@@ -258,9 +258,9 @@ class Lfm2ShortConvDecoderLayer(nn.Module):
self,
config: Lfm2Config,
layer_idx: int,
model_config: Optional[ModelConfig] = None,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
model_config: ModelConfig | None = None,
cache_config: CacheConfig | None = None,
quant_config: QuantizationConfig | None = None,
prefix: str = "",
) -> None:
super().__init__()
@@ -289,7 +289,7 @@ class Lfm2ShortConvDecoderLayer(nn.Module):
def forward(
self,
hidden_states: torch.Tensor,
residual: Optional[torch.Tensor],
residual: torch.Tensor | None,
**kwargs,
):
if residual is None:
@@ -365,8 +365,8 @@ class Lfm2Model(nn.Module):
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,
) -> torch.Tensor:
if get_pp_group().is_first_rank:
if inputs_embeds is not None:
@@ -532,8 +532,8 @@ class Lfm2ForCausalLM(
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,
) -> torch.Tensor:
hidden_states = self.model(