Add performance statistics display to mlc_llm serve command #2
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Outdated suggestions cannot be applied.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
Adds real-time performance monitoring to the
mlc_llm servecommand by displaying request completion statistics in the terminal. When a request finishes processing, users will now see performance metrics including token counts and throughput rates.Changes
cpp/serve/engine_actions/action_commons.cc:#include <cstdio>header for printf functionalityProcessFinishedRequestStateEntriesfunctionExample Output
Implementation Details
RequestMetricsdata with no additional computation overheadprintfwithfflushfor immediate console outputBenefits
The feature only displays statistics when meaningful data is available (both prefill and decode tokens > 0, with valid timing), ensuring clean output without noise from incomplete requests.
Testing
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.