Skip to content

[Wasm] Let the tokenizer bindings load HF and Tekken tokenizers #25103

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
abdelaziz-mahdy wants to merge 1 commit into
base: main
Choose a base branch
from
+18 −0
Open

[Wasm] Let the tokenizer bindings load HF and Tekken tokenizers #25103

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1011,6 +1011,11 @@ if(EXECUTORCH_BUILD_EXTENSION_LLM)
)
set(CMAKE_POSITION_INDEPENDENT_CODE ON)
endif()
if(EXECUTORCH_BUILD_TOKENIZERS_WASM)
# HF tokenizers (Llama 3, Qwen, Tekken...) use lookahead patterns that only
# the regex_lookahead engine supports.
set(SUPPORT_REGEX_LOOKAHEAD ON)
endif()
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/extension/llm/tokenizers)
if(EXECUTORCH_BUILD_EXTENSION_LLM_RUNNER
OR EXECUTORCH_BUILD_NATIVE_LLM_RUNNER
Expand Down
13 changes: 13 additions & 0 deletions extension/wasm/tokenizers/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,3 +39,16 @@ target_include_directories(
)

target_link_libraries(tokenizers_wasm PUBLIC ${link_libraries})

# The tokenizers library catches its own exceptions in normal operation: for
# example, HFTokenizer probes optional JSON keys and {"String": ...} patterns
# with try/catch. Emscripten disables exception catching unless -fexceptions
# is given, so without it those throws escape and load() fails on common
# tokenizer.json files. Compile the library and the bindings with it, and
# pass it on to the final link.
target_compile_options(tokenizers PRIVATE -fexceptions)
if(TARGET regex_lookahead)
target_compile_options(regex_lookahead PRIVATE -fexceptions)
endif()
target_compile_options(tokenizers_wasm PUBLIC -fexceptions)
target_link_options(tokenizers_wasm PUBLIC -fexceptions)
Loading