Skip to content

Conversation

CharlieFRuan
Copy link
Member

For certain tokenizer.json, huggingface's tokenizer would try to use thread parallelism, leading to error in wasm runtime. This PR sets TOKENIZERS_PARALLELISM to false when compiling for web, which huggingface/tokenizers reads in runtime.

See mlc-ai/mlc-llm#2601 for more.

@CharlieFRuan CharlieFRuan merged commit d5dd7f4 into mlc-ai:main Aug 12, 2024
CharlieFRuan added a commit to mlc-ai/web-llm that referenced this pull request Aug 12, 2024
### Changes
- Reorganized internal code, which should have no affect on behaviors
#536
- Bumped version of tokenizers-cpp to fix potential error `The global
thread pool has not been initialized.`
  - For more, see mlc-ai/tokenizers-cpp#42

### TVMjs
- Still compiled at
apache/tvm@1fcb620,
no change
jingyi-zhao-01 pushed a commit to jingyi-zhao-01/web-llm that referenced this pull request Dec 8, 2024
### Changes
- Reorganized internal code, which should have no affect on behaviors
mlc-ai#536
- Bumped version of tokenizers-cpp to fix potential error `The global
thread pool has not been initialized.`
  - For more, see mlc-ai/tokenizers-cpp#42

### TVMjs
- Still compiled at
apache/tvm@1fcb620,
no change
atebites-hub pushed a commit to atebites-hub/web-llm that referenced this pull request Oct 4, 2025
### Changes
- Reorganized internal code, which should have no affect on behaviors
mlc-ai#536
- Bumped version of tokenizers-cpp to fix potential error `The global
thread pool has not been initialized.`
  - For more, see mlc-ai/tokenizers-cpp#42

### TVMjs
- Still compiled at
apache/tvm@1fcb620,
no change
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant