Arm backend: profile SmolLM2 Ethos-U KV cache on FVP - #22560
Merged
Conversation
Capture per-inference Ethos-U85 PMU counters from the semihosting server. Separate token executions into prompt processing and decoding summaries. Disable FVP fast mode automatically during profiling. Support JSON and CSV reports, with optional NPU-only token-rate estimates. Document the CS-320 command and clarify that Cortex-M timing and end-to-end throughput cannot be inferred from the simulator. Generated with assistance from OpenAI Codex. Signed-off-by: Xingguo Li <xingguo.li@arm.com> Change-Id: Iba3ffb744f7b94aebdd51720f2634b221de87059
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22560
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 14f7672 with merge base c7bbe0b ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
zingo
approved these changes
Sep 4, 2026
sylvesterkaczmarek
left a comment
sylvesterkaczmarek
left a comment
There was a problem hiding this comment.
The profiling boundary is well defined. Re-enabling the PMU cycle counter at each server-mode measurement is necessary because StopMeasurements() disables it, and disabling Ethos-U fast mode only when profiling keeps the normal execution path unchanged. The phase accounting also documents the subtle first-generated-token ownership correctly, so the reported decode rate is not mislabeled as end-to-end throughput.
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
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.
Capture per-inference Ethos-U85 PMU counters from the semihosting server. Separate token executions into prompt processing and decoding summaries.
Disable FVP fast mode automatically during profiling. Support JSON and CSV reports, with optional NPU-only token-rate estimates.
Document the CS-320 command and clarify that Cortex-M timing and end-to-end throughput cannot be inferred from the simulator.
Generated with assistance from OpenAI Codex.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani