[Bug] lvm-llama-vision and lvm-llama-vision-guard failed processing requests

[lianhao]

Priority

Undecided

OS type

Ubuntu

Hardware type

Xeon-GNR

Installation method

• Pull docker images from hub.docker.com
• Build docker images from source

Deploy method

• Docker compose
• Docker
• Kubernetes
• Helm

Running nodes

Single Node

What's the version?

git commit 1cc4d21

Description

Following the lvm-llama-vision README, when test the service lvm-llama-vision or lvm-llama-vision-guard, it fails with the docker logs as listed below

Reproduce steps

Following the lvm-llama-vision README

Raw log

/home/user/.local/lib/python3.10/site-packages/pydantic/_internal/_fields.py:132: UserWarning: Field "model_name_or_path" in Audio2TextDoc has conflict with p
rotected namespace "model_".

You may be able to resolve this warning by setting `model_config['protected_namespaces'] = ()`.
  warnings.warn(
[2025-01-13 12:36:42,740] [    INFO] - Base service - CORS is enabled.
[2025-01-13 12:36:42,741] [    INFO] - Base service - Setting up HTTP server
[2025-01-13 12:36:42,741] [    INFO] - Base service - Uvicorn server setup on port 9399
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:9399 (Press CTRL+C to quit)
[2025-01-13 12:36:42,752] [    INFO] - Base service - HTTP server setup successful
INFO:     192.168.103.224:58408 - "POST /v1/lvm HTTP/1.1" 500 Internal Server Error
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/home/user/.local/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "/home/user/.local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
    return await self.app(scope, receive, send)
  File "/home/user/.local/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in __call__
    await super().__call__(scope, receive, send)
  File "/home/user/.local/lib/python3.10/site-packages/starlette/applications.py", line 113, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/home/user/.local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 187, in __call__
    raise exc
  File "/home/user/.local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 165, in __call__
    await self.app(scope, receive, _send) 
... ...
... ...
  File "/home/user/.local/lib/python3.10/site-packages/fastapi/routing.py", line 301, in app
    raw_response = await run_endpoint_function(
  File "/home/user/.local/lib/python3.10/site-packages/fastapi/routing.py", line 212, in run_endpoint_function
    return await dependant.call(**values)
  File "/home/user/comps/lvms/src/integrations/dependency/llama-vision/lvm.py", line 74, in lvm
    initialize()
  File "/home/user/comps/lvms/src/integrations/dependency/llama-vision/lvm.py", line 40, in initialize
    model = AutoModelForVision2Seq.from_pretrained(
  File "/home/user/.local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
  File "/home/user/.local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3372, in from_pretrained
    raise ImportError(
ImportError: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install 'accelerate>=0.26.0'`

Attachments

No response

[lianhao]

@lvliang-intel please take a look when you have bandwidth, thanks!

[xiguiw]

@lianhao
Seemed some package not installed.
Would you please some details? How do you set up then environment, especially requirements.txt files you installed with?

    return model_class.from_pretrained(
  File "/home/user/.local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3372, in from_pretrained
    raise ImportError(

[lianhao]

@lianhao Seemed some package not installed. Would you please some details? How do you set up then environment, especially requirements.txt files you installed with?

I'm following the lvm-llama-vision README to build the docker image, run and test.