add usage statistics for inference API #894
Open
+75
−8
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
dineshyv
requested review from
ashwinb,
yanxi0830,
hardikjshah,
dltn,
raghotham,
vladimirivic and
sixianyi0721
as code owners
facebook-github-bot
added
the
CLA Signed
dineshyv
changed the title
dineshyv
force-pushed
the
usage-statistics
branch
from
ead6cb9 to
6609362
Compare
|
@dineshyv I think you also want to regenerate the Open API spec so this get's updated: I think you just need to run |
vladimirivic
approved these changes
Jan 29, 2025
|
@raghotham any comments on generality / future-facing stuff? @dineshyv hold on for a couple hours before merging. |
ashwinb
requested changes
Jan 29, 2025
There was a problem hiding this comment.
This needs more discussion. Here is an alternate idea:
- we think of this as an extension of our telemetry API -- or rather telemetry needs to just work for this too.
- from that standpoint, we can make sure these stats get logged as "metrics" into our telemetry API and therefore can be queried
- this of course works only if the distro has a telemetry provider
however this is not sufficient because it makes for a terrible dev-ex for debugging while developing. when I want to understand usage I want each API calls usage to also be available. so how about all Llama Stack API calls are augmented by metrics?
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Outdated suggestions cannot be applied.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.
What does this PR do?
Adds a new usage field to inference APIs to indicate token counts for prompt and completion.