[V1][Metrics] Hook up IterationStats for Prometheus metrics #12478
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Follow on from vllm-project#12416 Pass IterationStats to the stat logger, and log them in both the logging and prometheus loggers. For the logging stat logger, we need to calculate the throughput based on the number of tokens in the particular logging interval. In the prometheus logger, we just need to record the prompt and generation tokens in a counter. Note, v0 had a vllm:tokens_total counter registered that apparently was never logged to, so I've omitted it in v1. Signed-off-by: Mark McLoughlin <[email protected]>
markmc
requested review from
DarkLight1337,
robertgshaw2-redhat,
simon-mo,
WoosukKwon,
njhill,
ywang96,
comaniac and
alexm-redhat
as code owners
|
👋 Hi! Thank you for contributing to the vLLM project. 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:
🚀 |
markmc
changed the title
robertgshaw2-redhat
approved these changes
Jan 28, 2025
|
LGTM |
robertgshaw2-redhat
added
the
ready
mgoin
approved these changes
Jan 28, 2025
rasmith
pushed a commit
to rasmith/vllm
that referenced
this pull request
Jan 30, 2025
…ject#12478) Signed-off-by: Mark McLoughlin <[email protected]>
Isotr0py
pushed a commit
to Isotr0py/vllm
that referenced
this pull request
Feb 2, 2025
…ject#12478) Signed-off-by: Mark McLoughlin <[email protected]> Signed-off-by: Isotr0py <[email protected]>
NickLucche
pushed a commit
to NickLucche/vllm
that referenced
this pull request
Feb 7, 2025
…ject#12478) Signed-off-by: Mark McLoughlin <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Follow on from #12416, part of #10582
Pass
IterationStatsto the stat logger, and log them in both the logging and prometheus loggers.For the logging stat logger, we need to calculate the throughput based on the number of tokens in the particular logging interval.
In the prometheus logger, we just need to record the prompt and generation tokens in a counter.
Note, v0 had a
vllm:tokens_totalcounter registered that apparently was never logged to, so I've omitted it in v1.