[llm_bench] Add batch considering in throughput and 2nd token latency for LLMPipeline #3108
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
as-suvorov
approved these changes
Dec 11, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
It was found that llm_bench shows very low throughput for speculative decode. This happens because llm_bench calculates the latency for tokens other than the first based on the
PerfMetricsraw_metrics.m_new_token_times, which do not take into account the batch.raw_metrics.m_durationsare also calculated based onraw_metrics.m_new_token_times, but the time is divided into batches, which significantly affects the calculations for speculative decoding.CVS-174513
Fixes #(issue)
Checklist: