vLLM doesn't estimate the model size properly

[Superskyyy]

Reproduction

In the current vLLM integration, the model size would be 0.000GB at startup (which I don't yet understand why), leading to an inaccurate profiling result and OOM after few steps. I will provide screenshot later.

System Info

• Transformers version: 4.48.2
• Accelerate version: 1.3.0
• Accelerate config: not found
• Datasets version: 3.2.0
• HF Hub version: 0.27.1
• TRL version: 0.15.0.dev0
• bitsandbytes version: not installed
• DeepSpeed version: 0.16.3
• Diffusers version: not installed
• Liger-Kernel version: 0.5.2
• LLM-Blender version: not installed
• OpenAI version: 1.60.2
• PEFT version: 0.14.0
• vLLM: 0.7.1

Checklist

• I have checked that my issue isn't already filed (see open issues)
• I have included my system information
• Any code provided is minimal, complete, and reproducible (more on MREs)
• Any code provided is properly formatted in code blocks, (no screenshot, more on code blocks)
• Any traceback provided is complete

[Superskyyy]

Screenshot:

[xx-Jiangwen]

same question