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

10
vllm/model_executor/models/llama_eagle.py
View File

@@ -1,6 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
from typing import Iterable, Set, Tuple
from collections.abc import Iterable
import torch
import torch.nn as nn
@@ -92,8 +92,8 @@ class LlamaModel(nn.Module):
hidden_states = hidden_states + residual
return hidden_states, 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)
(".qkv_proj", ".q_proj", "q"),
@@ -103,7 +103,7 @@ 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:
for param_name, weight_name, shard_id in stacked_params_mapping:
if weight_name not in name:
@@ -150,7 +150,7 @@ class EagleLlamaForCausalLM(LlamaForCausalLM):
) -> tuple[torch.Tensor, torch.Tensor]:
return self.model(input_ids, positions, 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,