Dynamic model class loading #101
Merged
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
5 tasks
timethink
pushed a commit
to timethink/sglang
that referenced
this pull request
Mar 9, 2025
NorthmanPKU
pushed a commit
to NorthmanPKU/sglang
that referenced
this pull request
May 16, 2025
…d input/output strides for kernel graphs. (sgl-project#98) * initial docs * update path * add doxygen files * add more * update docs * add more files * fix typo * link update * add gated mlp * add more tutorials * format * add transpiler docs * . * . * . * . * . * update RMSNorm example * adjust image width * Update LoRA tutorial * update files * fix typo * transpiler doc fix (sgl-project#89) * transpiler doc fix * fmt * . * checkpoint * Add files via upload * Update README.md * add file * add demo * update demo * minor changes * add input_strides into KNInputOp * support output_strides * transpiler add input/output stride (sgl-project#101) --------- Co-authored-by: Xinhao Cheng <99570243+xinhaoc@users.noreply.github.com> Co-authored-by: Zhihao Jia <zhihao@cmu.edu>
zhuyijie88
pushed a commit
to zhuyijie88/sglang
that referenced
this pull request
Sep 4, 2025
add dsr1 model
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Outdated suggestions cannot be applied.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.
This PR attempts to make the model loading process more systematic and self-contained. Currently when addinga new model, we have to explicitly import the model entry class in
model_runnter.load_modelfunction. This introduces two drawbacks:model_runner.pycannot focus on the changes of "model runner".model_runner.pyis easy to be missed and may result in conflicts.sglang.srtdoes not follow the standard Python package structure (i.e., leveraging__init__.pyto construct module hierarchy), so it's not straightforward to use a model registry with decorator. In this PR, I tried to dynamically scan all model files undermodels, and load their entry classes. The major drawback of this approach is that every model file has to haveEntryClassalias to be scanned. IMHO it should be relatively easy for developers to follow.Please share your thoughts.