[Quantization] support VPTQ

[wejoncy]

Motivation

@YangWang92

This PR is intended to add support for Extreme Low-bit Vector Post-Training Quantization (VPTQ) to vLLM.

More about VPTQ can be found at https://github.com/microsoft/vptq

VPTQ on Arxiv

VPTQ now support

• CUDA
• ROCM backend
• Tensor parallel.

Modifications

Support VPTQ for sglang.
Models from hf-hub are supported

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.