Skip to content

Fix /chat/completion response in echo mode#362

Merged
github-actions[bot] merged 3 commits intomainfrom
fix-echo
Feb 26, 2026
Merged

Fix /chat/completion response in echo mode#362
github-actions[bot] merged 3 commits intomainfrom
fix-echo

Conversation

@mayabar
Copy link
Collaborator

@mayabar mayabar commented Feb 26, 2026

Fixes #361

Signed-off-by: Maya Barnea <mayab@il.ibm.com>
Signed-off-by: Maya Barnea <mayab@il.ibm.com>
Signed-off-by: Maya Barnea <mayab@il.ibm.com>
@mayabar mayabar requested review from irar2 and shmuelk and removed request for irar2 February 26, 2026 14:43
@github-actions
Copy link

Typo Check Results

Found 1 potential typo in changed files:

File Issue Original Suggested Fix
pkg/llm-d-inference-sim/request.go Double space "Failed to tokenize echo mode response, " "Failed to tokenize echo mode response, "

Details: There's an extra space between "tokenize" and "echo" in the error message.


Domain terms dictionary (not flagged)

This checker recognizes llm-d domain terminology including: vLLM, NIXL, InferencePool, tokenizer, openaiserverapi, and many other technical terms specific to this repository.

Generated by Typo Checker for issue #362

@shmuelk
Copy link
Collaborator

shmuelk commented Feb 26, 2026

/lgtm
/approve

@github-actions github-actions bot added the lgtm Looks good to me, indicates that a PR is ready to be merged. label Feb 26, 2026
@mayabar mayabar requested review from irar2 and removed request for irar2 February 26, 2026 14:59
@github-actions github-actions bot merged commit cf682b5 into main Feb 26, 2026
11 checks passed
@github-actions github-actions bot deleted the fix-echo branch February 26, 2026 15:16
@mayabar mayabar mentioned this pull request Mar 1, 2026
github-actions bot pushed a commit that referenced this pull request Mar 2, 2026
* fix PR 362

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

* fix grpc in echo mode

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

---------

Signed-off-by: Maya Barnea <mayab@il.ibm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

lgtm Looks good to me, indicates that a PR is ready to be merged.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Bug: chat completions request in echo mode returns all messages instead of the latest only

2 participants