feat: Add vLLM counter metrics access through Triton #7493
Merged
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
yinggeh
requested review from
kthui,
rmccorm4,
GuanLuo,
krishung5 and
oandreeva-nv
11 tasks
yinggeh
changed the title
11 tasks
GuanLuo
approved these changes
Aug 9, 2024
kthui
approved these changes
Aug 9, 2024
|
remove gauge in the name of the PR |
yinggeh
changed the title
oandreeva-nv
previously approved these changes
Aug 9, 2024
… yinggeh-DLIS-7061-add-vllm-metrics
krishung5
previously approved these changes
Aug 9, 2024
kthui
previously approved these changes
Aug 9, 2024
GuanLuo
previously approved these changes
Aug 13, 2024
yinggeh
dismissed stale reviews from GuanLuo, kthui, oandreeva-nv, and krishung5
via
35cd4a3
yinggeh
force-pushed
the
yinggeh-DLIS-7061-add-vllm-metrics
branch
from
35cd4a3 to
6f601f4
Compare
… yinggeh-DLIS-7061-add-vllm-metrics
kthui
approved these changes
Aug 15, 2024
mc-nv
pushed a commit
that referenced
this pull request
Aug 19, 2024
Report vLLM counter metrics through Triton server
mc-nv
added a commit
that referenced
this pull request
Aug 19, 2024
Co-authored-by: Yingge He <[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Outdated suggestions cannot be applied.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.
What does the PR do?
Add vLLM counter metrics access through python_backend custom metrics.
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/vllm_backend#53
Where should the reviewer start?
n/a
Test plan:
L0_backend_vllm/metrics_test
17372863
Caveats:
n/a
Background
Customers requested.
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
n/a