forked from mlc-ai/mlc-llm
-
Notifications
You must be signed in to change notification settings - Fork 0
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.
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
[pull] main from mlc-ai:main #302
Merged
Merged
Conversation
This file contains 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
Typo engine.py
Relative Path causes this error. #2600 One can really only use an absolute path here
docs: Update model template link address
This PR migrates the implementation of the grammar engine to an external library XGrammar. The implementation of XGrammar is basically the same as our current version, but more modularized and robust. XGrammar will be continuously enhanced in the future. See https://github.com/mlc-ai/xgrammar for more details.
[docs] Updated path pointers in both docs files to point to the `conversation_template` directory instead of linking to the non-existent `conversation_template.py` file. Co-authored-by: 涧波 <[email protected]>
This PR bumps the 3rdparty/tokenizer-cpp. The SentencePiece tokenizer was disabled by default to reduce the binary size of the built library, while it causes some error when users expect to use the SentencePiece tokenizer. This PR enables it by default. And we will need to manually disable it if we need to reduce its binary size.
This PR fixes the function table initialization, so that when sliding window is enabled, we won't pick the FlashInfer attn kernel.
This PR bumps the 3rdparty tokenizers-cpp to update the HuggingFace tokenizers package dependency.
This PR adds the sentencepiece package as a Python installation requirement for tokenizer coverage when running `gen_config`.
Update deepseek_model.py
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.
See Commits and Changes for more details.
Created by pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )