-
Bug
-
Resolution: Duplicate
-
Undefined
-
rhelai-1.3
-
None
-
False
-
-
False
-
-
-
Important
-
Approved
To Reproduce Steps to reproduce the behavior:
- start container with instructlab-amd-rhel9:1.3-1732115458
- create config
- run 'ilab model serve'
- See traceback
$ ilab model serve INFO 2024-11-22 00:06:37,230 instructlab.model.serve_backend:56: Using model '/opt/app-root/src/.cache/instructlab/models/granite-8b-lab-v1' with -1 gpu-layers and 4096 max context size. INFO 2024-11-22 00:06:37,231 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 2024-11-22 00:06:37,232 instructlab.model.backends.vllm:313: vLLM starting up on pid 210 at http://127.0.0.1:8000/v1 Traceback (most recent call last): File "<frozen runpy>", line 189, in _run_module_as_main File "<frozen runpy>", line 112, in _get_module_details File "/opt/app-root/lib64/python3.11/site-packages/vllm/__init__.py", line 3, in <module> from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs File "/opt/app-root/lib64/python3.11/site-packages/vllm/engine/arg_utils.py", line 11, in <module> from vllm.config import (CacheConfig, ConfigFormat, DecodingConfig, File "/opt/app-root/lib64/python3.11/site-packages/vllm/config.py", line 12, in <module> from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/__init__.py", line 1, in <module> from vllm.model_executor.parameter import (BasevLLMParameter, File "/opt/app-root/lib64/python3.11/site-packages/vllm/model_executor/parameter.py", line 7, in <module> from vllm.distributed import get_tensor_model_parallel_rank File "/opt/app-root/lib64/python3.11/site-packages/vllm/distributed/__init__.py", line 1, in <module> from .communication_op import * File "/opt/app-root/lib64/python3.11/site-packages/vllm/distributed/communication_op.py", line 6, in <module> from .parallel_state import get_tp_group File "/opt/app-root/lib64/python3.11/site-packages/vllm/distributed/parallel_state.py", line 39, in <module> from vllm.utils import supports_custom_op File "/opt/app-root/lib64/python3.11/site-packages/vllm/utils.py", line 34, in <module> from rpdTracerControl import rpdTracerControl ModuleNotFoundError: No module named 'rpdTracerControl'
Expected behavior
- model to be served without error
Screenshots
- Attached Image
Device Info (please complete the following information):
- Hardware Specs: AMD MI300X x8
- OS Version: RHELAI 1.3
- Python Version: Python 3.11.7
- InstructLab Version: ilab, version 0.21.0
Additional context
- I am still working to reproduce in a bare metal install, will update once that work has been done
- blocks
-
RHELAI-2370 Add GradLib Support to ROCm Build
-
- Closed
-
- is related to
-
RHELAI-2370 Add GradLib Support to ROCm Build
-
- Closed
-