A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 08:15 UTC
[Bugfix] Fix QwenModel argument (#10262)
Signed-off-by: Jie Fu <jiefu@tencent.com>
Jie Fu (傅杰) committed
Nov 13, 2024 at 00:36 UTC
176fcb1c71655d825d2363e5f1468fa248fe783b
1 file changed
+2
-2
vllm/model_executor/models/qwen.py
+2
-2
@@ -1068,7 +1068,7 @@ class QWenLMHeadModel(QWenBaseModel, SupportsLoRA):
1068
config = vllm_config.model_config.hf_config
1069
# Initialize VL
1070
if hasattr(config, "visual"):
1071
- return QWenVL(vllm_config)
1071
+ return QWenVL(vllm_config=vllm_config)
1072
# Initialize LLM
1073
else:
1074
- return QWenLLM(vllm_config)
1074
+ return QWenLLM(vllm_config=vllm_config)