[Perf][MTP] Improve speculative decoding efficiency #2818
Closed
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Outdated suggestions cannot be applied.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.
Reduced kernel launch latency:
The original custom op library was too large, causing kernel launch latency to reach ~200µs. By using PyBind instead, launch latency was reduced to ~20µs.
Synchronization improvements:
Optimized several sync points in the speculative decoding path.
Conclusion:
In the ERNIE-LITE + MTP pipeline, the time from verify to the next main model C-Embedding was reduced from 8.5ms to 4ms(113%).