intel/llm-scaler-vllm:0.26.0-b2:: Gemma 12B model loading error #705

:: initializing oneAPI environment ...
   --: BASH_VERSION = 5.2.21(1)-release
   args: Using "$@" for setvars.sh arguments: --force
:: ccl -- latest
:: compiler -- latest
:: debugger -- latest
:: dev-utilities -- latest
:: dnnl -- latest
:: dpl -- latest
:: mkl -- latest
:: mpi -- latest
:: pti -- latest
:: tbb -- latest
:: umf -- latest
:: oneAPI environment initialized ::

WARNING 09-13 11:44:05 [argparse_utils.py:257] With `vllm serve`, you should provide the model as a positional argument or in a config file instead of via the `--model` option. The `--model` option will be removed in a future version.
INFO 09-13 11:44:05 [api_utils.py:345] 
INFO 09-13 11:44:05 [api_utils.py:345]        █     █     █▄   ▄█
INFO 09-13 11:44:05 [api_utils.py:345]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.26.1.dev0+g568afb3a1.d20260907
INFO 09-13 11:44:05 [api_utils.py:345]   █▄█▀ █     █     █     █  model   google/gemma-4-12B-it
INFO 09-13 11:44:05 [api_utils.py:345]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
INFO 09-13 11:44:05 [api_utils.py:345] 
INFO 09-13 11:44:05 [api_utils.py:273] non-default args: {'model_tag': 'google/gemma-4-12B-it', 'api_server_count': 1, 'enable_auto_tool_choice': True, 'tool_call_parser': 'gemma4', 'host': '127.0.0.1', 'model': 'google/gemma-4-12B-it', 'trust_remote_code': True, 'dtype': 'float16', 'quantization': 'fp8', 'enforce_eager': True, 'served_model_name': ['gemma-4-12b-it'], 'attention_backend': 'FLASH_ATTN', 'reasoning_parser': 'gemma4', 'tensor_parallel_size': 2, 'block_size': 64, 'gpu_memory_utilization': 0.9, 'kv_cache_dtype': 'fp8_e4m3', 'mamba_ssm_cache_dtype': 'float16', 'language_model_only': True, 'max_num_batched_tokens': 8192, 'speculative_config': {'model': 'google/gemma-4-12B-it-assistant', 'num_speculative_tokens': 4}}
INFO 09-13 11:44:05 [arg_utils.py:779] HF_HUB_OFFLINE is True, replace model_id [google/gemma-4-12B-it] to model_path [/root/.cache/huggingface/hub/models--google--gemma-4-12B-it/snapshots/707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7]
WARNING 09-13 11:44:05 [envs.py:2122] Unknown vLLM environment variable detected: VLLM_OFFLOAD_WEIGHTS_BEFORE_QUANT
Traceback (most recent call last):
  File "/opt/venv/bin/vllm", line 6, in <module>
    sys.exit(main())
             ^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 95, in main
    args.dispatch_function(args)
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 144, in cmd
    run_multi_api_server(args)
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 291, in run_multi_api_server
    vllm_config = engine_args.create_engine_config(usage_context=usage_context)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1880, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1639, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__
    s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
  Value error, The checkpoint you are trying to load has model type `gemma4_unified` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git` [type=value_error, input_value=ArgsKwargs((), {'model': ...nderer_num_workers': 1}), input_type=ArgsKwargs]
    For further information visit https://errors.pydantic.dev/2.13/v/value_error