-
Notifications
You must be signed in to change notification settings - Fork 86
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: Instrument latency without streaming duration #290
Merged
trallnag
merged 10 commits into
trallnag:master
from
dosuken123:track-response-start-duration
Mar 11, 2024
Merged
feat: Instrument latency without streaming duration #290
trallnag
merged 10 commits into
trallnag:master
from
dosuken123:track-response-start-duration
Mar 11, 2024
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
This commit adds a feature to track the latency excluding streaming duration.
dosuken123
force-pushed
the
track-response-start-duration
branch
from
March 4, 2024 02:27
ff9169e
to
019c8a5
Compare
dosuken123
changed the title
Track response start duration
Instrument latency without streaming duration
Mar 4, 2024
trallnag
changed the title
Instrument latency without streaming duration
feat: Instrument latency without streaming duration
Mar 11, 2024
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #290 +/- ##
==========================================
+ Coverage 95.79% 95.98% +0.19%
==========================================
Files 5 5
Lines 357 374 +17
==========================================
+ Hits 342 359 +17
Misses 15 15 ☔ View full report in Codecov by Sentry. |
Hi @dosuken123 thanks for the proposal and implementation. I will be included in the next version that will be released sometime this week |
@trallnag Thanks for help! Much appreciated 🙇 |
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 do?
This PR adds an option to track HTTP response duration without streaming duration.
Config Example:
https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/blob/main/ai_gateway/app.py?ref_type=heads#L51-58
Output example:
Fixes #291
Why do we need it?
Users often feel the latency as the first chunk arrival instead of the last chunk arrival as LLM inference APIs usually support HTTP streaming to improve the UX. We want to instrument the duration.
Who is this for?
GitLab, software developers, LLM app optimizations
Linked issues
Related to https://gitlab.com/gitlab-com/runbooks/-/merge_requests/6928#note_1796949998
Reviewer notes