add option to not increment endpoint retry limit

[jveronvialard]

What does this PR do?

Adds a no_infinite_endpoint_retries option for vLLM endpoints. When enabled, retryable endpoint errors no longer increase max_num_tries, so requests fail after the fixed retry limit instead of retrying indefinitely.

Checklist

• I have read the contributing guidelines.
• The change is focused; unrelated "drive-by" edits are tracked as separate issues/PRs.
• Tests added or updated and pass locally, or N/A for docs-only / non-code changes (so CI unit/server checks pass when applicable).
• Pre-commit checks pass locally (pre-commit run --all-files) (so CI lint/format/copyright pass).
• All commits have DCO sign-off (git commit -s) (so the DCO check passes).

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[cmunley1]

/ok to test 0859232