bugfix: expose prefix cache usage in responses#80
Draft
bupt-ycq wants to merge 1 commit into
Draft
Conversation
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
OutputUsageinto the internal usage modelusage.prompt_tokens_details.cached_tokensin streaming and non-streaming OpenAI responsesWhy
Prefix-cache token counts were dropped while converting RPC generation results into the service's internal usage model. As a result, OpenAI-compatible responses could not report how many prompt tokens were served from the prefix cache.
User impact
Clients can now observe prefix-cache effectiveness through
usage.prompt_tokens_details.cached_tokens. The field is present with0when no prompt tokens were cached.Tests
cmake --build build --target response_handler_usage_test xllm_rpc_service_test -j2build/tests/xllm_service/scheduler/response_handler_usage_test(2 tests passed)build/xllm_service/rpc_service/xllm_rpc_service_test(2 tests passed)