EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

remove qwen2.py llama.py fix llama output

Browse Source
This commit is contained in:
hanhaowen
2025-12-31 11:31:26 +08:00
parent b3c30a3cb9
commit b015bb76fd
11 changed files with 65 additions and 1263 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_kunlun/models/qwen3.py
View File

@@ -47,8 +47,8 @@ from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
from vllm.sequence import IntermediateTensors
from vllm.model_executor.models.interfaces import SupportsEagle3, SupportsLoRA, SupportsPP
from .qwen2 import Qwen2MLP as Qwen3MLP
from .qwen2 import Qwen2Model
from vllm.model_executor.models.qwen2 import Qwen2MLP as Qwen3MLP
from vllm.model_executor.models.qwen2 import Qwen2Model
from vllm.model_executor.models.utils import (AutoWeightsLoader, PPMissingLayer, extract_layer_index,
maybe_prefix)