[V1][Bug]: Consider sampler in memory profiling #13507
Description
Your current environment
The output of `python collect_env.py`
Your output of `python collect_env.py` here
🐛 Describe the bug
Currently, V1 model runner does not consider (or run) sampler during the initial memory profiling. This should be fixed 1) for more accurate memory profiling and 2) to warm up the sampler before processing any real requests.
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.