Add latency measurement for text models #44
Merged
Conversation
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
guangy10
force-pushed
the
et_modeling_refactor
branch
2 times, most recently
from
f0df2f8 to
16c238c
Compare
Merged
guangy10
force-pushed
the
et_modeling_refactor
branch
from
16c238c to
4d2dc1f
Compare
guangy10
force-pushed
the
et_modeling_refactor
branch
from
4d2dc1f to
f78a4a1
Compare
michaelbenayoun
approved these changes
Apr 7, 2025
Member
michaelbenayoun
left a comment
michaelbenayoun
left a comment
There was a problem hiding this comment.
LGTM from what I can understand.
This is great work but could you please try to make separate PRs by topics, like here we could have:
- A pr for the refactoring
- A pr for efficientnet
- A pr for stats computation
It is no big deal at all, but it makes things easier to review.
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Outdated suggestions cannot be applied.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.
stats.h) tooptimum-executorchin python. Eventually we could remove the py impl and utilize it from extensions/llm via pybind.ExecuTorchModelForSeq2SeqLMandExecuTorchModelForCausalLMmodeling.pyrefactor to reduce duplicate code:ExecuTorchModelBasethat represent the ExecuTorch inference model, with implementation of export, load from cache/hub, etc. common methods. Defined abstract methodforward,generate, etc. that each derived concrete class must implementExecuTorchModelForSeq2SeqLM,ExecuTorchModelForCausalLM, etc.) lightweight and easy to scaleefficientnetmodel. Conditionally run only when executorch >= 0.6 (so it will run on the pinned nightly). Previously broken due to a bug a in XNNPACK, which has been fixed and picked to the upcomingexecutorch 0.6release.