feat(serve): report timings during prompt progress - #163
Open
hecrj wants to merge 1 commit into
Open
Conversation
Attach the llama.cpp-compatible timings snapshot to Chat Completions prompt-progress chunks when timings_per_token is enabled, alongside the existing prompt_progress payload. While the prompt is still being processed the snapshot is prompt-only: the predicted fields stay zero, prompt_ms is the wall time elapsed since committed admission, and the prompt rates span the processed suffix rather than the complete prompt. The Engine PromptProgress event already carries the required elapsed clock, so the change stays inside the serving adapter. Update the serving documentation and schema tests together with the protocol behavior.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Attaches the llama.cpp-compatible
timingssnapshot to Chat Completions prompt-progress chunks whentimings_per_tokenis enabled, alongside the existingprompt_progresspayload.