[feature-request] Update vLLM library in LMI containers to v0.6.0

[CoolFish88]

Concise Description:

vLLM v0.6.0 provides 2.7x throughput improvement and 5x latency reduction over the previous version (v0.5.3)

DLC image/dockerfile:
763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-lmi11.0.0-cu124
763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-neuronx-sdk2.19.1

Is your feature request related to a problem? Please describe.
Improve the performance of LMI containters

Describe the solution you'd like
Update vLLM library in LMI containers to v0.6.0

[siddvenk]

We are planning a release that will include vllm 0.6.2 within the next 2 weeks. In the meantime, you can try providing a requirements.txt with vllm==0.6.x and leverage a later version of vllm that way. If you go this route, you should also set OPTION_ROLLING_BATCH=vllm environment variable to force usage of vllm

[n0thing233]

@siddvenk,
are the dockerfile or image building process of LMI containers open-sourced?
Appreciate if you could share.

If not, I think I'll need to build an image on top of LMI image, am I correct? some dockerfile like this:

FROM 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.31.0-lmi13.0.0-cu124

RUN pip install --upgrade vllm==0.7.2