[UPSTREAM-SYNC] Feat: Add invocation of Post response plugins #132
Conversation
This file contains hidden or 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
Signed-off-by: Shmuel Kallner <[email protected]>
Signed-off-by: Shmuel Kallner <[email protected]>
shaneutt
approved these changes
May 7, 2025
elevran
changed the title
elevran
approved these changes
May 7, 2025
| result, err = s.scheduler.OnResponse(ctx, llmReq, reqCtx.TargetPod) | ||
| if err != nil { | ||
| logger.V(logutil.DEFAULT).Error(err, "Error handling response") | ||
| reqCtx.ResponseStatusCode = errutil.ModelServerError |
There was a problem hiding this comment.
q: will returning an error not send the response back to the user?
If this is an internal logic failure and we've already compute the LLM response, might be wasteful.
Co-authored-by: Etai Lev Ran <[email protected]>
Signed-off-by: Shmuel Kallner <[email protected]>
Signed-off-by: Shmuel Kallner <[email protected]>
Signed-off-by: Shmuel Kallner <[email protected]>
Signed-off-by: Shmuel Kallner <[email protected]>
nirrozenbaum
reviewed
May 8, 2025
Comment on lines
+221
to
+226
| for _, pod := range pods { | ||
| if pod.GetPod().NamespacedName.String() == targetPodName { | ||
| targetPod = pod | ||
| break | ||
| } | ||
| } |
There was a problem hiding this comment.
if a pod was selected scheduler and crashed before this call, what happens here?
targetPod remains nil?
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Outdated suggestions cannot be applied.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.
This PR adds the invocation of any configured PostResponse plugins during the processing of responses from the chosen inference server. It also enables the PostResponse plugin to add/modify headers that are ultimately sent to the client.