Conversation
Signed-off-by: Kai Xu <kaix@nvidia.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1240 +/- ##
=======================================
Coverage 76.91% 76.91%
=======================================
Files 350 350
Lines 40480 40480
=======================================
Hits 31137 31137
Misses 9343 9343
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
What does this PR do?
Type of change: ?
Add EXTRA_PIP_DEPS support to the launcher's
ptq.shso models requiring extra pip packages (e.g.,mamba-ssmfor hybrid Mamba architectures like Nemotron) can install them automatically before running PTQ. Also updates the PTQ skill with a new Step 2.5 for detecting model-specific dependencies.Usage
Set EXTRA_PIP_DEPS in the launcher YAML's environment section:
Testing
Tested end-to-end: NVFP4 quantization of
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16on a B200 cluster via the launcher. Job succeeded: mamba-ssm installed automatically, calibration completed (512 samples, 84s), checkpoint exported (18 GB, 2 safetensor shards).Before your PR is "Ready for review"
Make sure you read and follow Contributor guidelines and your commits are signed (
git commit -s -S).Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded
trust_remote_code=True,torch.load(..., weights_only=False),pickle, etc.).CONTRIBUTING.md: ✅ / ❌ / N/AAdditional Information