bash-5.1# ILAB_HOME=/var/home/devcloud ilab model serve 
INFO 2024-11-26 13:35:12,849 instructlab.model.serve_backend:56: Using model '/var/home/devcloud/.cache/instructlab/models/granite-7b-redhat-lab' with -1 gpu-layers and 4096 max context size.
INFO 2024-11-26 13:35:12,849 instructlab.model.serve_backend:88: '--gpus' flag used alongside '--tensor-parallel-size' in the vllm_args section of the config file. Using value of the --gpus flag.
INFO 2024-11-26 13:35:12,851 instructlab.model.backends.vllm:313: vLLM starting up on pid 4 at http://127.0.0.1:8000/v1
/usr/lib64/python3.11/inspect.py:389: FutureWarning: `torch.distributed.reduce_op` is deprecated, please use `torch.distributed.ReduceOp` instead
  return isinstance(object, types.FunctionType)
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 33, in <module>
    from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/serving_chat.py", line 28, in <module>
    from vllm.model_executor.guided_decoding import (
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/guided_decoding/__init__.py", line 6, in <module>
    from vllm.model_executor.guided_decoding.lm_format_enforcer_decoding import (
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py", line 15, in <module>
    from vllm.model_executor.guided_decoding.outlines_decoding import (
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/guided_decoding/outlines_decoding.py", line 13, in <module>
    from vllm.model_executor.guided_decoding.outlines_logits_processors import (
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/guided_decoding/outlines_logits_processors.py", line 24, in <module>
    from outlines.caching import cache
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/__init__.py", line 2, in <module>
    import outlines.generate
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/generate/__init__.py", line 2, in <module>
    from .cfg import cfg
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/generate/cfg.py", line 5, in <module>
    from outlines.models import OpenAI
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/models/__init__.py", line 10, in <module>
    from .exllamav2 import ExLlamaV2Model, exl2
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/models/exllamav2.py", line 9, in <module>
    from .transformers import TransformerTokenizer
  File "/opt/app-root/lib64/python3.11/site-packages/outlines/models/transformers.py", line 3, in <module>
    from datasets.fingerprint import Hasher
  File "/opt/app-root/lib64/python3.11/site-packages/datasets/__init__.py", line 17, in <module>
    from .arrow_dataset import Dataset
  File "/opt/app-root/lib64/python3.11/site-packages/datasets/arrow_dataset.py", line 60, in <module>
    import pyarrow as pa
  File "/opt/app-root/lib64/python3.11/site-packages/pyarrow/__init__.py", line 65, in <module>
    import pyarrow.lib as _lib
ImportError: /lib64/libjemalloc.so.2: cannot allocate memory in static TLS block