-
Notifications
You must be signed in to change notification settings - Fork 190
Add a deprecation notice for trtllm export in doc #410
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
Conversation
WalkthroughAdded deprecation notice and migration guidance for export_tensorrt_llm_checkpoint, updated internal reference URLs to legacy paths, and added an introductory note that ModelOpt can automatically convert ModelOpt-exported LLM checkpoints to TensorRT-LLM checkpoints and engines. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Nitpick comments (1)
docs/source/deployment/1_tensorrt_llm.rst (1)
5-6: Use Sphinx’s.. deprecated::directive instead of bold textSphinx provides a first-class
.. deprecated::admonition that adds consistent styling and version metadata to the doc build. Please switch to that directive (with the appropriate version) so the deprecation is surfaced uniformly in HTML/PDF outputs.-**Deprecation Notice**: The export_tensorrt_llm_checkpoint API will be deprecated in future releases. Users are encouraged to transition to the :doc:`unified HF export API <3_unified_hf>`, which provides enhanced functionality and flexibility for exporting models to multiple inference frameworks including TensorRT-LLM, vLLM, and SGLang. +.. deprecated:: <version> + The :meth:`export_tensorrt_llm_checkpoint <modelopt.torch.export.model_config_export.export_tensorrt_llm_checkpoint>` API will be removed in an upcoming release. Transition to the :doc:`unified HF export API <3_unified_hf>` for expanded export coverage across TensorRT-LLM, vLLM, and SGLang.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/deployment/1_tensorrt_llm.rst(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: build-docs
- GitHub Check: code-quality
|
I recommend we fully deprecate this page and move the hf checkpoint page to be the default. We might want to update the supported models for TRT LLM as well. |
Signed-off-by: Zhiyu Cheng <[email protected]>
Signed-off-by: Zhiyu Cheng <[email protected]>
87171ad to
89d7937
Compare
Let's please do that when the trt-llm export related code is fully removed in hf_ptq examples. |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #410 +/- ##
==========================================
- Coverage 73.79% 73.36% -0.44%
==========================================
Files 171 180 +9
Lines 17591 17919 +328
==========================================
+ Hits 12982 13146 +164
- Misses 4609 4773 +164 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
What does this PR do?
Type of change: Doc update
Overview: Add a deprecation notice for trtllm export in doc.
Usage
# Add a code snippet demonstrating how to use thisTesting
Before your PR is "Ready for review"
Additional Information
Summary by CodeRabbit