9038865261
### What this PR does / why we need it?
Considering that long queues severely impact the developer experience,
we have decided to make the following changes:
1. Changes will use the self_hosted runner
2. e2e-2card will use the A3 node.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>