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

11
vllm/model_executor/models/chatglm.py
View File

@@ -3,7 +3,8 @@
# https://github.com/THUDM/ChatGLM2-6B
"""Inference-only ChatGLM model compatible with THUDM weights."""
import json
from typing import Iterable, Optional, Set, Tuple, Union
from collections.abc import Iterable
from typing import Optional, Union
import torch
from torch import nn
@@ -358,15 +359,15 @@ class ChatGLMModel(nn.Module, SupportsQuant):
return hidden_states
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)
("linear_proj.merged_proj", "linear_proj.gate_proj", 0),
("linear_proj.merged_proj", "linear_proj.dense_h_to_4h", 1),
]
params_dict = dict(self.named_parameters())
loaded_params: Set[str] = set()
loaded_params: set[str] = set()
for name, loaded_weight in weights:
for (param_name, weight_name, shard_id) in stacked_params_mapping:
@@ -440,7 +441,7 @@ class ChatGLMBaseModel(nn.Module):
sampling_metadata)
return logits
def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
loader = AutoWeightsLoader(self)
return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)