[Misc] Update benchmark to support image_url file or http

[kakao-steve-ai]

For testing ShareGPT4V dataset in benchmarks/benchmark_serving.py, the part setting image_url was updated slightly.

Client Usage:

python3 benchmarks/benchmark_serving.py --backend openai-chat \
    --base-url http://127.0.0.1:8000/v1 \
    --endpoint /chat/completions \
    --model llava-hf/llava-v1.6-mistral-7b-hf \
    --dataset-path Lin-Chen/ShareGPT4V \
    --dataset-name hf --hf-subset ShareGPT4V \
    --hf-split train \
    --num-prompts=100

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[comaniac]

LGTM. cc @lk-chen