[V1][Metrics] Add per-request prompt/generation_tokens histograms

[markmc]

Follow on from #12478, part of #10582

Observe these values as requests are finished.

Requires keeping track of generated tokens per-request to handle streaming delta updates.

[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.

🚀

[robertgshaw2-redhat]

QQ, in V0, we did:

histogram.labels(**self.labels).observe(datum)

vllm/vllm/engine/metrics.py

Line 541 in 0f657bd

histogram.labels(**self.labels).observe(datum)

Do you know why this is or is not needed?

[robertgshaw2-redhat]

Ill hit automerge to unblock you

[markmc]

labels() is a pretty expensive factory method and our labels aren't ever changing, so I'm building these labelled metrics in the PrometheusStatLogger constructor

self.histogram_num_generation_tokens_request = \
            prometheus_client.Histogram(
                name="vllm:request_generation_tokens",
                documentation="Number of generation tokens processed.",
                buckets=build_1_2_5_buckets(max_model_len),
                labelnames=labelnames).labels(*labelvalues)

Not so easy to spot it though!