[Bug]: Model architectures ['LlavaForConditionalGeneration'] are not supported for now.

[DwenGu]

Your current environment

The output of `python collect_env.py`

WARNING 10-15 15:24:09 cuda.py:22] You are using a deprecated `pynvml` package. Please install `nvidia-ml-py` instead, and make sure to uninstall `pynvml`. When both of them are installed, `pynvml` will take precedence and cause errors. See https://pypi.org/project/pynvml for more information.
Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at https://github.com/opencv/opencv-python/issues/884 to correct your environment. The import of cv2 has been skipped.
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.2
Libc version: glibc-2.35

Python version: 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-118-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.6.68
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA L20
Nvidia driver version: 550.90.12
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.4.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.4.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               160
On-line CPU(s) list:                  0-159
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8460Y+
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   40
Socket(s):                            2
Stepping:                             8
CPU max MHz:                          3700.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4000.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            3.8 MiB (80 instances)
L1i cache:                            2.5 MiB (80 instances)
L2 cache:                             160 MiB (80 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-39,80-119
NUMA node1 CPU(s):                    40-79,120-159
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cudnn-frontend==1.6.0
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-dali-cuda120==1.41.0
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-modelopt==0.15.1
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvimgcodec-cu12==0.3.0.5
[pip3] nvidia-nvjitlink-cu12==12.6.77
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] nvidia-pyindex==1.0.9
[pip3] onnx==1.16.2
[pip3] optree==0.12.1
[pip3] pynvml==11.4.1
[pip3] pytorch-triton==3.0.0+dedb7bdf3
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torch_tensorrt==2.5.0a0
[pip3] torchvision==0.19.0
[pip3] transformers==4.45.2
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.dev189+g16b24e7d

Model Input Dumps

No response

🐛 Describe the bug

vllm serve llava-hf/llava-1.5-13b-hf --dtype auto --api-key token-abc123

ValueError: Model architectures ['LlavaForConditionalGeneration'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'ArcticForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'JAISLMHeadModel', 'JambaForCausalLM', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MambaForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'Phi3SmallForCausalLM', 'PhiMoEForCausalLM', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'XverseForCausalLM', 'BartModel', 'BartForConditionalGeneration', 'MistralModel', 'Qwen2ForRewardModel', 'Gemma2Model', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'FuyuForCausalLM', 'InternVLChatModel', 'LlavaForConditionalGeneration', 'LlavaNextForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MiniCPMV', 'MolmoForCausalLM', 'NVLM_D', 'PaliGemmaForConditionalGeneration', 'Phi3VForCausalLM', 'PixtralForConditionalGeneration', 'QWenLMHeadModel', 'Qwen2VLForConditionalGeneration', 'UltravoxModel', 'MllamaForConditionalGeneration', 'EAGLEModel', 'MedusaModel', 'MLPSpeculatorPreTrainedModel']

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[DarkLight1337]

Can you post the full error log, including any warnings before that?

[DwenGu]

vllm serve llava-hf/llava-1.5-13b-hf --dtype auto --api-key token-abc123

The whole log:
WARNING 10-16 05:20:41 cuda.py:22] You are using a deprecated pynvmlpackage. Please installnvidia-ml-pyinstead, and make sure to uninstallpynvml. When both of them are installed, pynvmlwill take precedence and cause errors. See https://pypi.org/project/pynvml for more information. Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at https://github.com/opencv/opencv-python/issues/884 to correct your environment. The import of cv2 has been skipped. /usr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash: No module named 'vllm._version' from vllm.version import __version__ as VLLM_VERSION INFO 10-16 05:20:43 api_server.py:528] vLLM API server version dev INFO 10-16 05:20:43 api_server.py:529] args: Namespace(subparser='serve', model_tag='llava-hf/llava-1.5-13b-hf', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key='token-abc123', lora_modules=None, prompt_adapters=None, chat_template=None, response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='llava-hf/llava-1.5-13b-hf', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, download_dir=None, load_format='auto', config_format='auto', dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=None, guided_decoding_backend='outlines', distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=1, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=False, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, enforce_eager=False, max_context_len_to_capture=None, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, override_neuron_config=None, scheduling_policy='fcfs', disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, dispatch_function=<function serve at 0x7fa292ca30a0>) INFO 10-16 05:20:43 api_server.py:166] Multiprocessing frontend to use ipc:///tmp/ddbcaa5c-cdf7-4ccb-88b7-5213dc35d525 for IPC Path. INFO 10-16 05:20:43 api_server.py:179] Started engine process with PID 673 WARNING 10-16 05:20:45 cuda.py:22] You are using a deprecatedpynvmlpackage. Please installnvidia-ml-pyinstead, and make sure to uninstallpynvml. When both of them are installed, pynvmlwill take precedence and cause errors. See https://pypi.org/project/pynvml for more information. Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at https://github.com/opencv/opencv-python/issues/884 to correct your environment. The import of cv2 has been skipped. /usr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash: No module named 'vllm._version' from vllm.version import __version__ as VLLM_VERSION ERROR 10-16 05:20:48 registry.py:264] Error in inspecting model architecture 'LlavaForConditionalGeneration' ERROR 10-16 05:20:48 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 426, in _run_in_subprocess ERROR 10-16 05:20:48 registry.py:264] returned.check_returncode() ERROR 10-16 05:20:48 registry.py:264] File "/usr/lib/python3.10/subprocess.py", line 457, in check_returncode ERROR 10-16 05:20:48 registry.py:264] raise CalledProcessError(self.returncode, self.args, self.stdout, ERROR 10-16 05:20:48 registry.py:264] subprocess.CalledProcessError: Command '['/usr/bin/python', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1. ERROR 10-16 05:20:48 registry.py:264] ERROR 10-16 05:20:48 registry.py:264] The above exception was the direct cause of the following exception: ERROR 10-16 05:20:48 registry.py:264] ERROR 10-16 05:20:48 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 262, in _try_inspect_model_cls ERROR 10-16 05:20:48 registry.py:264] return model.inspect_model_cls() ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 224, in inspect_model_cls ERROR 10-16 05:20:48 registry.py:264] return _run_in_subprocess( ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 429, in _run_in_subprocess ERROR 10-16 05:20:48 registry.py:264] raise RuntimeError(f"Error raised in subprocess:\n" ERROR 10-16 05:20:48 registry.py:264] RuntimeError: Error raised in subprocess: ERROR 10-16 05:20:48 registry.py:264] Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at https://github.com/opencv/opencv-python/issues/884 to correct your environment. The import of cv2 has been skipped. ERROR 10-16 05:20:48 registry.py:264] /usr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash: ERROR 10-16 05:20:48 registry.py:264] No module named 'vllm._version' ERROR 10-16 05:20:48 registry.py:264] from vllm.version import __version__ as VLLM_VERSION ERROR 10-16 05:20:48 registry.py:264] /usr/lib/python3.10/runpy.py:126: RuntimeWarning: 'vllm.model_executor.models.registry' found in sys.modules after import of package 'vllm.model_executor.models', but prior to execution of 'vllm.model_executor.models.registry'; this may result in unpredictable behaviour ERROR 10-16 05:20:48 registry.py:264] warn(RuntimeWarning(msg)) ERROR 10-16 05:20:48 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:48 registry.py:264] File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main ERROR 10-16 05:20:48 registry.py:264] return _run_code(code, main_globals, None, ERROR 10-16 05:20:48 registry.py:264] File "/usr/lib/python3.10/runpy.py", line 86, in _run_code ERROR 10-16 05:20:48 registry.py:264] exec(code, run_globals) ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 450, in <module> ERROR 10-16 05:20:48 registry.py:264] _run() ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 443, in _run ERROR 10-16 05:20:48 registry.py:264] result = fn() ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 225, in <lambda> ERROR 10-16 05:20:48 registry.py:264] lambda: _ModelInfo.from_model_cls(self.load_model_cls())) ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 228, in load_model_cls ERROR 10-16 05:20:48 registry.py:264] mod = importlib.import_module(self.module_name) ERROR 10-16 05:20:48 registry.py:264] File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module ERROR 10-16 05:20:48 registry.py:264] return _bootstrap._gcd_import(name[level:], package, level) ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap>", line 1050, in _gcd_import ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap>", line 1027, in _find_and_load ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap>", line 688, in _load_unlocked ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap_external>", line 883, in exec_module ERROR 10-16 05:20:48 registry.py:264] File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llava.py", line 21, in <module> ERROR 10-16 05:20:48 registry.py:264] from .clip import (CLIPVisionModel, dummy_image_for_clip, ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/clip.py", line 10, in <module> ERROR 10-16 05:20:48 registry.py:264] from transformers.models.clip.modeling_clip import CLIPSdpaAttention ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 44, in <module> ERROR 10-16 05:20:48 registry.py:264] from ...modeling_flash_attention_utils import _flash_attention_forward ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_flash_attention_utils.py", line 27, in <module> ERROR 10-16 05:20:48 registry.py:264] from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/flash_attn/__init__.py", line 3, in <module> ERROR 10-16 05:20:48 registry.py:264] from flash_attn.flash_attn_interface import ( ERROR 10-16 05:20:48 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/flash_attn/flash_attn_interface.py", line 10, in <module> ERROR 10-16 05:20:48 registry.py:264] import flash_attn_2_cuda as flash_attn_cuda ERROR 10-16 05:20:48 registry.py:264] ImportError: /usr/local/lib/python3.10/dist-packages/flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE ERROR 10-16 05:20:48 registry.py:264] Traceback (most recent call last): File "/usr/local/bin/vllm", line 8, in <module> sys.exit(main()) File "/usr/local/lib/python3.10/dist-packages/vllm/scripts.py", line 195, in main args.dispatch_function(args) File "/usr/local/lib/python3.10/dist-packages/vllm/scripts.py", line 41, in serve uvloop.run(run_server(args)) File "/usr/local/lib/python3.10/dist-packages/uvloop/__init__.py", line 82, in run return loop.run_until_complete(wrapper()) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/usr/local/lib/python3.10/dist-packages/uvloop/__init__.py", line 61, in wrapper return await main File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 552, in run_server async with build_async_engine_client(args) as engine_client: File "/usr/lib/python3.10/contextlib.py", line 199, in __aenter__ return await anext(self.gen) File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 107, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/usr/lib/python3.10/contextlib.py", line 199, in __aenter__ return await anext(self.gen) File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 184, in build_async_engine_client_from_engine_args engine_config = engine_args.create_engine_config() File "/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py", line 900, in create_engine_config model_config = self.create_model_config() File "/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py", line 837, in create_model_config return ModelConfig( File "/usr/local/lib/python3.10/dist-packages/vllm/config.py", line 194, in __init__ self.multimodal_config = self._init_multimodal_config( File "/usr/local/lib/python3.10/dist-packages/vllm/config.py", line 213, in _init_multimodal_config if ModelRegistry.is_multimodal_model(architectures): File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 384, in is_multimodal_model return self.inspect_model_cls(architectures).supports_multimodal File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 353, in inspect_model_cls return self._raise_for_unsupported(architectures) File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 314, in _raise_for_unsupported raise ValueError( ValueError: Model architectures ['LlavaForConditionalGeneration'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'ArcticForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'JAISLMHeadModel', 'JambaForCausalLM', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MambaForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'Phi3SmallForCausalLM', 'PhiMoEForCausalLM', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'XverseForCausalLM', 'BartModel', 'BartForConditionalGeneration', 'MistralModel', 'Qwen2ForRewardModel', 'Gemma2Model', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'FuyuForCausalLM', 'InternVLChatModel', 'LlavaForConditionalGeneration', 'LlavaNextForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MiniCPMV', 'MolmoForCausalLM', 'NVLM_D', 'PaliGemmaForConditionalGeneration', 'Phi3VForCausalLM', 'PixtralForConditionalGeneration', 'QWenLMHeadModel', 'Qwen2VLForConditionalGeneration', 'UltravoxModel', 'MllamaForConditionalGeneration', 'EAGLEModel', 'MedusaModel', 'MLPSpeculatorPreTrainedModel'] ERROR 10-16 05:20:52 registry.py:264] Error in inspecting model architecture 'LlavaForConditionalGeneration' ERROR 10-16 05:20:52 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 426, in _run_in_subprocess ERROR 10-16 05:20:52 registry.py:264] returned.check_returncode() ERROR 10-16 05:20:52 registry.py:264] File "/usr/lib/python3.10/subprocess.py", line 457, in check_returncode ERROR 10-16 05:20:52 registry.py:264] raise CalledProcessError(self.returncode, self.args, self.stdout, ERROR 10-16 05:20:52 registry.py:264] subprocess.CalledProcessError: Command '['/usr/bin/python', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1. ERROR 10-16 05:20:52 registry.py:264] ERROR 10-16 05:20:52 registry.py:264] The above exception was the direct cause of the following exception: ERROR 10-16 05:20:52 registry.py:264] ERROR 10-16 05:20:52 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 262, in _try_inspect_model_cls ERROR 10-16 05:20:52 registry.py:264] return model.inspect_model_cls() ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 224, in inspect_model_cls ERROR 10-16 05:20:52 registry.py:264] return _run_in_subprocess( ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 429, in _run_in_subprocess ERROR 10-16 05:20:52 registry.py:264] raise RuntimeError(f"Error raised in subprocess:\n" ERROR 10-16 05:20:52 registry.py:264] RuntimeError: Error raised in subprocess: ERROR 10-16 05:20:52 registry.py:264] Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at https://github.com/opencv/opencv-python/issues/884 to correct your environment. The import of cv2 has been skipped. ERROR 10-16 05:20:52 registry.py:264] /usr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash: ERROR 10-16 05:20:52 registry.py:264] No module named 'vllm._version' ERROR 10-16 05:20:52 registry.py:264] from vllm.version import __version__ as VLLM_VERSION ERROR 10-16 05:20:52 registry.py:264] /usr/lib/python3.10/runpy.py:126: RuntimeWarning: 'vllm.model_executor.models.registry' found in sys.modules after import of package 'vllm.model_executor.models', but prior to execution of 'vllm.model_executor.models.registry'; this may result in unpredictable behaviour ERROR 10-16 05:20:52 registry.py:264] warn(RuntimeWarning(msg)) ERROR 10-16 05:20:52 registry.py:264] Traceback (most recent call last): ERROR 10-16 05:20:52 registry.py:264] File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main ERROR 10-16 05:20:52 registry.py:264] return _run_code(code, main_globals, None, ERROR 10-16 05:20:52 registry.py:264] File "/usr/lib/python3.10/runpy.py", line 86, in _run_code ERROR 10-16 05:20:52 registry.py:264] exec(code, run_globals) ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 450, in <module> ERROR 10-16 05:20:52 registry.py:264] _run() ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 443, in _run ERROR 10-16 05:20:52 registry.py:264] result = fn() ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 225, in <lambda> ERROR 10-16 05:20:52 registry.py:264] lambda: _ModelInfo.from_model_cls(self.load_model_cls())) ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 228, in load_model_cls ERROR 10-16 05:20:52 registry.py:264] mod = importlib.import_module(self.module_name) ERROR 10-16 05:20:52 registry.py:264] File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module ERROR 10-16 05:20:52 registry.py:264] return _bootstrap._gcd_import(name[level:], package, level) ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap>", line 1050, in _gcd_import ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap>", line 1027, in _find_and_load ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap>", line 688, in _load_unlocked ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap_external>", line 883, in exec_module ERROR 10-16 05:20:52 registry.py:264] File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llava.py", line 21, in <module> ERROR 10-16 05:20:52 registry.py:264] from .clip import (CLIPVisionModel, dummy_image_for_clip, ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/clip.py", line 10, in <module> ERROR 10-16 05:20:52 registry.py:264] from transformers.models.clip.modeling_clip import CLIPSdpaAttention ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 44, in <module> ERROR 10-16 05:20:52 registry.py:264] from ...modeling_flash_attention_utils import _flash_attention_forward ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_flash_attention_utils.py", line 27, in <module> ERROR 10-16 05:20:52 registry.py:264] from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/flash_attn/__init__.py", line 3, in <module> ERROR 10-16 05:20:52 registry.py:264] from flash_attn.flash_attn_interface import ( ERROR 10-16 05:20:52 registry.py:264] File "/usr/local/lib/python3.10/dist-packages/flash_attn/flash_attn_interface.py", line 10, in <module> ERROR 10-16 05:20:52 registry.py:264] import flash_attn_2_cuda as flash_attn_cuda ERROR 10-16 05:20:52 registry.py:264] ImportError: /usr/local/lib/python3.10/dist-packages/flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE ERROR 10-16 05:20:52 registry.py:264] Process SpawnProcess-1: Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 392, in run_mp_engine engine = MQLLMEngine.from_engine_args(engine_args=engine_args, File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 137, in from_engine_args engine_config = engine_args.create_engine_config() File "/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py", line 900, in create_engine_config model_config = self.create_model_config() File "/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py", line 837, in create_model_config return ModelConfig( File "/usr/local/lib/python3.10/dist-packages/vllm/config.py", line 194, in __init__ self.multimodal_config = self._init_multimodal_config( File "/usr/local/lib/python3.10/dist-packages/vllm/config.py", line 213, in _init_multimodal_config if ModelRegistry.is_multimodal_model(architectures): File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 384, in is_multimodal_model return self.inspect_model_cls(architectures).supports_multimodal File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 353, in inspect_model_cls return self._raise_for_unsupported(architectures) File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/registry.py", line 314, in _raise_for_unsupported raise ValueError( ValueError: Model architectures ['LlavaForConditionalGeneration'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'ArcticForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'GraniteForCausalLM', 'GraniteMoeForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'JAISLMHeadModel', 'JambaForCausalLM', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MambaForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiniCPMForCausalLM', 'MiniCPM3ForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OlmoeForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'Phi3SmallForCausalLM', 'PhiMoEForCausalLM', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'SolarForCausalLM', 'XverseForCausalLM', 'BartModel', 'BartForConditionalGeneration', 'MistralModel', 'Qwen2ForRewardModel', 'Gemma2Model', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'FuyuForCausalLM', 'InternVLChatModel', 'LlavaForConditionalGeneration', 'LlavaNextForConditionalGeneration', 'LlavaNextVideoForConditionalGeneration', 'LlavaOnevisionForConditionalGeneration', 'MiniCPMV', 'MolmoForCausalLM', 'NVLM_D', 'PaliGemmaForConditionalGeneration', 'Phi3VForCausalLM', 'PixtralForConditionalGeneration', 'QWenLMHeadModel', 'Qwen2VLForConditionalGeneration', 'UltravoxModel', 'MllamaForConditionalGeneration', 'EAGLEModel', 'MedusaModel', 'MLPSpeculatorPreTrainedModel'] root@98fe23bde663:/workspace#

[DarkLight1337]

Can you force-reinstall vLLM? The error logs suggest an issue with importing vllm._version module, which shouldn't happen on the current version.

Also, in the future please properly format your error logs as they are very difficult to read.

[DwenGu]

Can you force-reinstall vLLM? The error logs suggest an issue with importing vllm._version module, which shouldn't happen on the current version.

Also, in the future please properly format your error logs as they are very difficult to read.

Thanks for your kind reply. Will try it.

[DwenGu]

I use the command pip install --force-reinstall vllm and try python -c "import vllm"
The error is the same like:

WARNING 10-16 06:11:55 cuda.py:22] You are using a deprecated pynvml package. Please install nvidia-ml-py instead, and make sure to uninstall pynvml. When both of them are installed, pynvml will take precedence and cause errors. See https://pypi.org/project/pynvml for more information.
Warning: Your installation of OpenCV appears to be broken: module 'cv2.dnn' has no attribute 'DictValue'.Please follow the instructions at opencv/opencv-python#884 to correct your environment. The import of cv2 has been skipped.
/usr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash:
No module named 'vllm._version'
from vllm.version import version as VLLM_VERSION

[DarkLight1337]

There seems to be another error:

ImportError: /usr/local/lib/python3.10/dist-packages/flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE 

You might have to install vLLM in a fresh environment.

[DwenGu]

There seems to be another error:

ImportError: /usr/local/lib/python3.10/dist-packages/flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE 

You might have to install vLLM in a fresh environment.

I will do that. Thanks~

[DwenGu]

using the. nvcr.io/nvidia/pytorch:23.10-py3 and pip install vllm can solve the issue.
However, still occur the

sr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash:
No module named 'vllm._version'
  from vllm.version import __version__ as VLLM_VERSION

[DarkLight1337]

cc @dtrifiro

[dtrifiro]

@DarkLight1337 I'm aware of the issue. It seems that the pypi wheel wasn't built correctly, see discussion here: #4738 (comment)

also reported in #9182 (comment)

[DarkLight1337]

sr/local/lib/python3.10/dist-packages/vllm/connections.py:8: RuntimeWarning: Failed to read commit hash:
No module named 'vllm._version'
from vllm.version import version as VLLM_VERSION

This shouldn't crash your code so you can ignore this when using vLLM.