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

[fix]matmul not support cuda graph

Browse Source
This commit is contained in:
Li Wei
2026-01-06 16:07:29 +08:00
parent 515a4eeda9
commit 9533f68e99
3 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_kunlun/models/qwen3_vl_moe.py
View File

@@ -42,7 +42,7 @@ from vllm.model_executor.model_loader.weight_utils import (
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm.sequence import IntermediateTensors
from vllm.model_executor.models.qwen3_moe import Qwen3MoeForCausalLM, Qwen3MoeModel
from vllm_kunlun.models.qwen3_moe import Qwen3MoeForCausalLM, Qwen3MoeModel
from vllm.model_executor.models.qwen3_vl import (Qwen3_VisionTransformer, Qwen3VLDummyInputsBuilder,
Qwen3VLForConditionalGeneration,
Qwen3VLMultiModalProcessor, Qwen3VLProcessingInfo)