Migrate to PyTorch tokenizers #781
Merged
+36,974
−300
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
benITo47
requested review from
chmjkb and
msluszniak
and removed request for
chmjkb
benITo47
force-pushed
the
@bo/change_tokenizers
branch
from
e896b8e to
cc00c58
Compare
msluszniak
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
msluszniak
added
executorch
chmjkb
requested changes
Feb 4, 2026
Collaborator
chmjkb
left a comment
chmjkb
left a comment
There was a problem hiding this comment.
Please fix tests b4 merging 👍🏻
packages/react-native-executorch/common/rnexecutorch/host_objects/JsiConversions.h
Outdated
Show resolved
Hide resolved
chmjkb
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Show resolved
Hide resolved
chmjkb
requested changes
Feb 4, 2026
Collaborator
chmjkb
left a comment
chmjkb
left a comment
There was a problem hiding this comment.
Please remove the Error.get() calls
mkopcins
reviewed
Feb 4, 2026
Comment on lines
+356
to
+358
| inline jsi::Value getJsiValue(bool val, jsi::Runtime &runtime) { | ||
| return jsi::Value(val); | ||
| } |
Collaborator
There was a problem hiding this comment.
I think this should be above the template and below
inline jsi::Value getJsiValue(int val, jsi::Runtime &runtime) {
return {runtime, val};
}
Member
There was a problem hiding this comment.
Could you tell the reason for that, aesthetic one?
Contributor
Author
There was a problem hiding this comment.
+1 for msluszniak.
Could you elaborate?
mkopcins
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
mkopcins
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
mkopcins
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
chmjkb
requested changes
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/TokenizerModule.cpp
Outdated
Show resolved
Hide resolved
mkopcins
reviewed
Feb 4, 2026
| if (result.ok()) { | ||
| return static_cast<uint64_t>(result.get()); // TODO: CHANGE RETURN TYPE | ||
| } | ||
| return -1; |
Collaborator
There was a problem hiding this comment.
like above, maybe reject promise on js side
mkopcins
reviewed
Feb 4, 2026
msluszniak
reviewed
Feb 4, 2026
packages/react-native-executorch/common/rnexecutorch/host_objects/JsiConversions.h
Show resolved
Hide resolved
benITo47
force-pushed
the
@bo/change_tokenizers
branch
from
752f379 to
8aaf940
Compare
msluszniak
approved these changes
Feb 4, 2026
chmjkb
reviewed
Feb 4, 2026
Collaborator
chmjkb
left a comment
chmjkb
left a comment
There was a problem hiding this comment.
looks good on my end, thank u 🙏🏻
Member
|
@chmjkb I guess you wanted to approve, not add another review ;) |
chmjkb
approved these changes
Feb 4, 2026
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.
Description
This PR migrates us from tokenisers-cpp to PyTorch tokenisers bundled with executorch
Introduces a breaking change?
Type of change
Tested on
Testing instructions
This changes need to be tested manually. Try running all our apps that consume tokenizers and see whether the output is ok.
By "OK" I mean
Related issues
Checklist