how to inference with vllm?
#48
by
tomatoChenBM
- opened
I used to inference model with vllm to provide an OpenAI-Compatible Server, but it seems that this model doesn't support vllm inference.
And how can I inference with transformers? The doc doesn't provide any command to inference the model.
Hi @tomatoChenBM , you can start the OpenAI-Compatible Server by using the following command:
python -m vllm.entrypoints.openai.api_server --model 'microsoft/Phi-4-multimodal-instruct' --dtype auto --trust-remote-code --max-model-len 131072 --enable-lora --max-lora-rank 320 --lora-extra-vocab-size 0 --limit-mm-per-prompt audio=3,image=3 --max-loras 2 --lora-modules speech=<path to speech lora folder> vision=<path to vision lora folder>
The speech lora and vision lora folders are within the Phi-4-multimodal-instruct folder downloaded by vLLM, you can also use the following script to find thoses:
from huggingface_hub import snapshot_download
model_path = snapshot_download(repo_id="microsoft/Phi-4-multimodal-instruct")
speech_lora_path = model_path+"/speech-lora"
vision_lora_path = model_path+"/vision-lora"
Hi @tomatoChenBM , you can start the OpenAI-Compatible Server by using the following command:
python -m vllm.entrypoints.openai.api_server --model 'microsoft/Phi-4-multimodal-instruct' --dtype auto --trust-remote-code --max-model-len 131072 --enable-lora --max-lora-rank 320 --lora-extra-vocab-size 0 --limit-mm-per-prompt audio=3,image=3 --max-loras 2 --lora-modules speech=<path to speech lora folder> vision=<path to vision lora folder>The speech lora and vision lora folders are within the Phi-4-multimodal-instruct folder downloaded by vLLM, you can also use the following script to find thoses:
from huggingface_hub import snapshot_download model_path = snapshot_download(repo_id="microsoft/Phi-4-multimodal-instruct") speech_lora_path = model_path+"/speech-lora" vision_lora_path = model_path+"/vision-lora"
it seems that vllm does not support this model: ↓
[ValueError: Model architectures ['Phi4MMForCausalLM'] are not supported for now.](ValueError: Model architectures ['Phi4MMForCausalLM'] are not supported for now. Supported architectures: dict_keys(['AquilaModel', 'AquilaForCausalLM', 'ArcticForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'InternLM2VEForCausalLM', 'JAISLMHeadModel', 'JambaForCausalLM', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MambaForCausalLM', 'FalconMambaForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'Phi3SmallForCausalLM', 'PhiMoEForCausalLM', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'XverseForCausalLM', 'BartModel', 'BartForConditionalGeneration', 'Florence2ForConditionalGeneration', 'BertModel', 'RobertaModel', 'XLMRobertaModel', 'Gemma2Model', 'LlamaModel', 'MistralModel', 'Qwen2Model', 'Qwen2ForRewardModel', 'Qwen2ForSequenceClassification', 'LlavaNextForConditionalGeneration', 'Phi3VForCausalLM', 'Qwen2VLForConditionalGeneration', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'FuyuForCausalLM', 'H2OVLChatModel', 'InternVLChatModel', 'Idefics3ForConditionalGeneration', 'LlavaForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MiniCPMV', 'MolmoForCausalLM', 'NVLM_D', 'PaliGemmaForConditionalGeneration', 'PixtralForConditionalGeneration', 'QWenLMHeadModel', 'Qwen2AudioForConditionalGeneration', 'UltravoxModel', 'MllamaForConditionalGeneration', 'EAGLEModel', 'MedusaModel', 'MLPSpeculatorPreTrainedModel']))