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_vl_moe.py
View File

@@ -42,8 +42,8 @@ from vllm.model_executor.model_loader.weight_utils import (
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm.sequence import IntermediateTensors
from .qwen3_moe import Qwen3MoeForCausalLM, Qwen3MoeModel
from .qwen3_vl import (Qwen3_VisionTransformer, Qwen3VLDummyInputsBuilder,
from vllm.model_executor.models.qwen3_moe import Qwen3MoeForCausalLM, Qwen3MoeModel
from vllm.model_executor.models.qwen3_vl import (Qwen3_VisionTransformer, Qwen3VLDummyInputsBuilder,
Qwen3VLForConditionalGeneration,
Qwen3VLMultiModalProcessor, Qwen3VLProcessingInfo)
from vllm.model_executor.models.utils import is_pp_missing_parameter, maybe_prefix