vLLM Error: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now.

#7
by HaoyuHuang - opened

vllm version: 0.6.0
vllm-flash-attn: 2.6.1
transformers: 4.44.2
torch: 2.4.0

llm = LLM(
model='./MiniCPM3-4B/',
trust_remote_code=True,
tensor_parallel_size=1
)

ValueError: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'JAISLMHeadModel', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiniCPMForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'PhiMoEForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'ArcticForCausalLM', 'XverseForCausalLM', 'Phi3SmallForCausalLM', 'MedusaModel', 'EAGLEModel', 'MLPSpeculatorPreTrainedModel', 'JambaForCausalLM', 'GraniteForCausalLM', 'MistralModel', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'FuyuForCausalLM', 'InternVLChatModel', 'LlavaForConditionalGeneration', 'LlavaNextForConditionalGeneration', 'MiniCPMV', 'PaliGemmaForConditionalGeneration', 'Phi3VForCausalLM', 'UltravoxModel', 'BartModel', 'BartForConditionalGeneration']

OpenBMB org

For now, you need to install our forked version of vLLM. We have updated the README.

Thanks! But what do you mean "our forked version of vLLM"? I'm sorry that I couldn't find your content about vLLM in README.md file.

OpenBMB org

see here:

pip install git+https://github.com/OpenBMB/vllm.git@minicpm3
neoz changed discussion status to closed

see here:

pip install git+https://github.com/OpenBMB/vllm.git@minicpm3

got the error below

subprocess.CalledProcessError: Command '['cmake', '/tmp/pip-req-build-4230nddm', '-G', 'Ninja', '-DCMAKE_BUILD_TYPE=RelWithDebInfo', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/tmp/pip-req-build-4230nddm/build/lib.linux-x86_64-cpython-311/vllm', '-DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=build/temp.linux-x86_64-cpython-311', '-DVLLM_TARGET_DEVICE=cuda', '-DVLLM_PYTHON_EXECUTABLE=/data/aaa/envs/aa_minicpm_py311/bin/python', '-DNVCC_THREADS=1', '-DCMAKE_JOB_POOL_COMPILE:STRING=compile', '-DCMAKE_JOB_POOLS:STRING=compile=128']' returned non-zero exit status 1.
[end of output]
OpenBMB org

@JinChe vLLM has officially supported MiniCPM3-4B since 0.6.2. You can directly install it using pip.

Sign up or log in to comment