Support modelopt pre-quantized model in llm

[lanluo-nvidia]

Description

This is to support the modelopt pre-quantized model in LLM

#not pre-quantized model, directly inference with fp16/bf16
python run_llm.py --model Qwen/Qwen2.5-0.5B-Instruct \
--prompt "What is parallel programming?" \
--model_precision FP16 --num_tokens 128 \
--cache static_v2 --enable_pytorch_run

# not pre-quantized model, use modelopt to quantize and inference
python run_llm.py --model Qwen/Qwen2.5-0.5B-Instruct  \
--prompt "What is parallel programming?"  \
--quant_format fp8 --num_tokens 128 \
--cache static_v2 --enable_pytorch_run

# nvidia modelopt fp8 prequantized model
python run_llm.py --model nvidia/Qwen3-8B-FP8 \
--prompt "What is parallel programming?"  \
--num_tokens 128 \
--cache static_v2 --enable_pytorch_run

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified