[Android] Use ms for number report #5362
Closed
Conversation
This file contains 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
ns * 1e-6 = ms
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5362
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 11d53dd with merge base 034e098 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
guangy10
reviewed
Sep 13, 2024
| @@ -106,14 +106,14 @@ public void onGenerationStopped() { | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "model_load_time(ns)", | |||
huydhn
reviewed
Sep 13, 2024
| @@ -106,14 +106,14 @@ public void onGenerationStopped() { | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "model_load_time(ns)", | |||
There was a problem hiding this comment.
Nit: The metric value is now in (ms) instead of (ns), so its name need to be updated accordingly
huydhn
reviewed
Sep 13, 2024
| @@ -106,14 +106,14 @@ public void onGenerationStopped() { | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "model_load_time(ns)", | |||
| mStatsDump.loadEnd - mStatsDump.loadStart, | |||
| (mStatsDump.loadEnd - mStatsDump.loadStart) * 1e-6, | |||
| 0.0f)); | |||
| // LLM generate time | |||
| results.add( | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "generate_time(ns)", | |||
There was a problem hiding this comment.
Same comment about the metric name
guangy10
reviewed
Sep 13, 2024
| @@ -106,14 +106,14 @@ public void onGenerationStopped() { | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "model_load_time(ns)", | |||
| mStatsDump.loadEnd - mStatsDump.loadStart, | |||
| (mStatsDump.loadEnd - mStatsDump.loadStart) * 1e-6, | |||
| 0.0f)); | |||
| // LLM generate time | |||
| results.add( | |||
| new BenchmarkMetric( | |||
| benchmarkModel, | |||
| "generate_time(ns)", | |||
guangy10
approved these changes
Sep 13, 2024
|
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
|
@kirklandsign merged this pull request in 62024d8. |
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.
ns * 1e-6 = ms
Example output:
(9.36ms inference mv2_xnnpack)
and for LLM
(12.34 tps mocked number)