我想让服务化ip为服务器ip以便于其他机器调用，如下是执行命令和报错信息：
root@55afa35d6faa:/home/model_weights/MindSDK# vllm serve /home/model_weights/MindSDK/Qwen3-30B-A3B/ --master-addr {服务器ip}--port 8800 -tp 4 --gpu-memory-utilization 0.9 --enable_expert_parallel
INFO 11-19 07:25:35 [__init__.py:36] Available plugins for group vllm.platform_plugins:
INFO 11-19 07:25:35 [__init__.py:38] - ascend -> vllm_ascend:register
INFO 11-19 07:25:35 [__init__.py:41] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.
INFO 11-19 07:25:35 [__init__.py:207] Platform plugin ascend is activated
WARNING 11-19 07:25:39 [_custom_ops.py:20] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3VLMoeForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLMoeForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2_5_VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl:AscendQwen2_5_VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2_5OmniModel is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_omni_thinker:AscendQwen2_5OmniThinkerForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture DeepseekV32ForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.deepseek_v3_2:CustomDeepseekV3ForCausalLM.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3NextForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen3_next:CustomQwen3NextForCausalLM.
INFO 11-19 07:25:40 [importing.py:63] Triton not installed or not compatible; certain GPU-related functions will not be available.
usage: vllm [-h] [-v] {chat,complete,serve,bench,collect-env,run-batch} ...
vllm: error: unrecognized arguments: --master-addr {服务器ip}
点赞
收藏
回复
分享
举报
已解决
我想让服务化ip为服务器ip以便于其他机器调用，如下是执行命令和报错信息：
root@55afa35d6faa:/home/model_weights/MindSDK# vllm serve /home/model_weights/MindSDK/Qwen3-30B-A3B/ --master-addr {服务器ip}--port 8800 -tp 4 --gpu-memory-utilization 0.9 --enable_expert_parallel
INFO 11-19 07:25:35 [__init__.py:36] Available plugins for group vllm.platform_plugins:
INFO 11-19 07:25:35 [__init__.py:38] - ascend -> vllm_ascend:register
INFO 11-19 07:25:35 [__init__.py:41] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.
INFO 11-19 07:25:35 [__init__.py:207] Platform plugin ascend is activated
WARNING 11-19 07:25:39 [_custom_ops.py:20] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3VLMoeForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLMoeForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2_5_VLForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_vl:AscendQwen2_5_VLForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen2_5OmniModel is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen2_5_omni_thinker:AscendQwen2_5OmniThinkerForConditionalGeneration.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture DeepseekV32ForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.deepseek_v3_2:CustomDeepseekV3ForCausalLM.
WARNING 11-19 07:25:40 [registry.py:582] Model architecture Qwen3NextForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen3_next:CustomQwen3NextForCausalLM.
INFO 11-19 07:25:40 [importing.py:63] Triton not installed or not compatible; certain GPU-related functions will not be available.
usage: vllm [-h] [-v] {chat,complete,serve,bench,collect-env,run-batch} ...
vllm: error: unrecognized arguments: --master-addr {服务器ip}