Compatible with transformers 5.0 at TurboMind side

[lvhan028]

No description provided.

[Copilot]

Pull request overview

This PR aims to make lmdeploy compatible with transformers 5.0 at the TurboMind side. Transformers 5.0 introduced a breaking change where rope-related parameters (including rope_theta and rope_scaling) are now aggregated into a single rope_parameters dictionary in the model configuration.

Changes:

• Removed unused utility functions from lmdeploy/vl/model/utils.py including weight loading helpers and import hacks
• Added support for the new rope_parameters structure in transformers 5.0 for LlamaModel while maintaining backward compatibility with older versions
• Added similar rope_parameters support for DeepSeek2Model

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
lmdeploy/vl/model/utils.py	Cleaned up by removing unused functions: load_weight_ckpt, get_used_weight_files, load_model_from_weight_files, add_sys_path, and hack_import_with
lmdeploy/turbomind/deploy/source_model/llama.py	Added conditional logic to check for rope_parameters (transformers 5.0) and extract rope_theta and rope_scaling from it, with fallback to the old structure for backward compatibility
lmdeploy/turbomind/deploy/source_model/deepseek2.py	Added similar conditional logic to handle rope_parameters for DeepSeek2 models

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The rope_theta value retrieved from rope_parameters is not explicitly converted to float, unlike line 140 which uses float(model_arg.get('rope_theta', 10000.0)). For consistency and to ensure type safety, this should be: rope_theta = float(rope_scaling.get('rope_theta', 10000.0)).

Suggested change

	rope_theta = rope_scaling.get('rope_theta', 10000.0)
	rope_theta = float(rope_scaling.get('rope_theta', 10000.0))

[RunningLeon]

v5 broke for vl model

lmdeploy/lmdeploy/vl/model/utils.py", line 12, in <module>
from transformers.utils import (SAFE_WEIGHTS_INDEX_NAME, SAFE_WEIGHTS_NAME, WEIGHTS_INDEX_NAME, WEIGHTS_NAME,
ImportError: cannot import name 'is_safetensors_available' from 'transformers.utils' (/nvme1/xxx/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/utils/__init__.py)