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

Update deprecated type hinting in models (#18132)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-15 06:06:50 +01:00
committed by GitHub
parent 83f74c698f
commit 26d0419309
130 changed files with 971 additions and 901 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/model_executor/models/llama_eagle3.py
View File

@@ -1,6 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
from typing import Iterable, Optional, Set, Tuple
from collections.abc import Iterable
from typing import Optional
import torch
import torch.nn as nn
@@ -56,7 +57,7 @@ class LlamaDecoderLayer(LlamaDecoderLayer):
embeds: torch.Tensor,
hidden_states: torch.Tensor,
residual: Optional[torch.Tensor],
) -> Tuple[torch.Tensor, torch.Tensor]:
) -> tuple[torch.Tensor, torch.Tensor]:
residual = hidden_states
embeds = self.input_layernorm(embeds)
@@ -140,8 +141,8 @@ class LlamaModel(nn.Module):
hidden_states, hidden_prenorm = self.norm(hidden_states, residual)
return hidden_states, hidden_prenorm
def load_weights(self, weights: Iterable[Tuple[str,
torch.Tensor]]) -> Set[str]:
def load_weights(self, weights: Iterable[tuple[str,
torch.Tensor]]) -> set[str]:
stacked_params_mapping = [
# (param_name, shard_name, shard_id)
(".qkv_proj", ".q_proj", "q"),
@@ -151,7 +152,7 @@ class LlamaModel(nn.Module):
(".gate_up_proj", ".up_proj", 1),
]
params_dict = dict(self.named_parameters())
loaded_params: Set[str] = set()
loaded_params: set[str] = set()
for name, loaded_weight in weights:
if 'midlayer.' in name:
name = name.replace('midlayer.', 'layers.0.')
@@ -228,7 +229,7 @@ class Eagle3LlamaForCausalLM(LlamaForCausalLM):
# combine multiple auxiliary hidden states returned by eagle3
return self.model.fc(hidden_states)
def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
loader = AutoWeightsLoader(
self,
skip_prefixes=None,