1. Add --profile flag to attention_benchmark to output Highway profiler - #1010
Merged
Conversation
copybara-service
Bot
force-pushed
the
test_974965807
branch
4 times, most recently
from
September 4, 2026 16:12
4eb314e to
2fbbc92
Compare
zone breakdowns when compiled with -DPROFILER_ENABLED=1. 2. Link //third_party/highway:profiler into attention_benchmark in BUILD. 3. Instrument DSpark speculative decoding stages (Gen.MTP.Draft, Gen.MTP.VerifyPass, Gen.MTP.CommitDSparkKV) in deepseek_spec.cc with PROFILER_ZONE markers. 4. Add GCPP_ZONE profiling instrumentation to DeepSeek V4 MLA attention (ComputeQKV, DotSoftmax, SumHeads) and dense FFW in deepseek.cc. 5. Add PrintResults() call under #if PROFILER_ENABLED to run_dsv4.cc. PiperOrigin-RevId: 976362424
copybara-service
Bot
force-pushed
the
test_974965807
branch
from
September 4, 2026 16:45
2fbbc92 to
61cc7d0
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
zone breakdowns when compiled with -DPROFILER_ENABLED=1.
Gen.MTP.VerifyPass, Gen.MTP.CommitDSparkKV) in deepseek_spec.cc with
PROFILER_ZONE markers.
(ComputeQKV, DotSoftmax, SumHeads) and dense FFW in deepseek.cc.