diff --git a/CMakeLists.txt b/CMakeLists.txt
index 43cfe244b87..1a27134bfde 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -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
diff --git a/extension/wasm/tokenizers/CMakeLists.txt b/extension/wasm/tokenizers/CMakeLists.txt
index a1bead4bb80..6997b2bceed 100644
--- a/extension/wasm/tokenizers/CMakeLists.txt
+++ b/extension/wasm/tokenizers/CMakeLists.txt
@@ -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)