[LLM] Custom models - #1001
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Enterprise Run ID: 📒 Files selected for processing (5)
📝 WalkthroughWalkthroughThe change adds local model support for SGLang and vLLM. Absolute model paths no longer create Hugging Face installables. Tests cover this behavior, and workload documentation describes required mounts and model files. ChangesLocal model loading
Estimated code review effort: 2 (Simple) | ~10 minutes Merge Risk: ⚪ Minimal · up to This change adds custom-model support for vLLM and SGLang with accompanying documentation and tests; no actionable merge-blocking risk remains. Suggested reviewers: 🚥 Pre-merge checks | ✅ 4✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
Summary
Allow custom models for vLLM and SGLang
Test Plan
Additional Notes