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

12
vllm/model_executor/models/telechat2.py
View File

@@ -19,7 +19,7 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Iterable, Set, Tuple
from collections.abc import Iterable
import torch
import torch.nn as nn
@@ -50,14 +50,14 @@ class TeleChat2Model(LlamaModel):
layer.mlp.gate_up_proj.bias = None
layer.mlp.gate_up_proj.skip_bias_add = True
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 = [
('gate_up_proj', 'gate_proj', 0),
('gate_up_proj', 'up_proj', 1),
]
params_dict = dict(self.named_parameters())
loaded_params: Set[str] = set()
loaded_params: set[str] = set()
total_num_heads = self.config.n_head
head_dim = self.config.hidden_size // total_num_heads
for name, loaded_weight in weights:
@@ -128,8 +128,8 @@ class TeleChat2ForCausalLM(LlamaForCausalLM):
layer_type: type[nn.Module] = LlamaDecoderLayer):
return TeleChat2Model(vllm_config=vllm_config, prefix=prefix)
def load_weights(self, weights: Iterable[Tuple[str,
torch.Tensor]]) -> Set[str]:
def load_weights(self, weights: Iterable[tuple[str,
torch.Tensor]]) -> set[str]:
loader = AutoWeightsLoader(
self,