fix(cloud-edge-llm): fix environment setup crashes and dependency typos

[rakshaak29]

Resolves #393

Description

This PR resolves critical setup failure issues in the cloud-edge-collaborative-inference-for-llm example that blocked macOS and CPU-only users from installing dependencies and running the benchmark.

Changes Made:

• requirements.txt:
  • Removed vllm (CUDA/Linux only) to make it an optional, conditionally loaded backend.
  • Corrected datamodel_code_generator to datamodel-code-generator.
  • Added missing runtime dependency retry.
• test_queryrouting.yaml:
  • Commented out the vllm backend in the default configuration so the example executes successfully out-of-the-box falling back to huggingface.

Testing Done

• Validated pip install -r requirements.txt completes successfully without CUDA.
• Ensured CloudModel successfully runs utilizing the imported retry mechanics without ImportError.

[kubeedge-bot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: rakshaak29
To complete the pull request process, please assign moorezheng after the PR has been reviewed.
You can assign the PR to them by writing /assign @moorezheng in a comment when ready.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[gemini-code-assist]

Code Review

This pull request enhances the portability of LLM examples by replacing absolute paths with relative ones, updating the BaseModel to use a public Hugging Face model ID, and implementing dynamic device selection (CUDA/MPS/CPU). It also updates project dependencies and ignores local development artifacts. Review feedback suggests refining the MPS availability check for better compatibility, deduplicating the model identifier string, and specifying a minimum version for the torch dependency.

[Rishabh-git10]

Hi @rakshaak29, thanks for putting this together. Shifting the default config to huggingface is a great improvement for accessibility, but I ran into a blocker during setup.

The example fails to launch because colorlog is missing from requirements.txt. Please add this dependency to examples/cloud-edge-collaborative-inference-for-llm/requirements.txt.

Reproduced error:

...$ pip install -r examples/cloud-edge-collaborative-inference-for-llm/requirements.txt
...
...$ ianvs -f examples/cloud-edge-collaborative-inference-for-llm/benchmarkingjob.yaml
...
File ".../core/common/log.py", line 18, in <module>
    import colorlog
ModuleNotFoundError: No module named 'colorlog'

A few other notes:

• This PR mixes fixes for cloud-edge-llm with path fixes for llm_simple_qa. I strongly recommend isolating the llm_simple_qa path fixes into a separate PR. Keeping the history clean makes it much easier for the maintainers to track what actually changed and why.
• I noticed venv311/ was added. Please use a generic venv/ pattern instead; it ensures portability since different contributors use different Python versions.

[Chidroopakanaparthy]

Reproduction result:

Checked out pr-394. Changes confined to
examples/cloud-edge-collaborative-inference-for-llm/ only.

Key diff:

-vllm 
-datamodel_code_generator
+datamodel-code-generator
+retry
+torch>=2.0.0
+vllm # Uncomment for Linux + CUDA environments only

Removing vllm is a critical fix, its wheel build fails on macOS entirely, blocking pip install -r requirements.txt for all Mac contributors.

Note for smart_coding: this example has no requirements.txt at all. This PR establishes the minimum viable pattern. A dedicated PR should create examples/smart_coding/requirements.txt with at minimum:
torch>=2.0.0, transformers, openai, accelerate, tqdm, numpy.

Recommendation: Merge.