List view
Areas of focus: - Batch inference serving - EPP next-hop proxy exploration - Token in/out support
No due dateAreas of focus - Implement and document well lit paths for - Multi-model/LoRA - Disaggregated P/D - Data parallel serving - SLO and priorities - Support autoscaler scale from zero - DX improvements - Remove Python dependencies from code base / CICD - Streamline docker builds - Extend integration and end-to-end tests
Due by January 11, 2026•1/19 issues closed- Overdue by 2 month(s)•Due by October 5, 2025•10/11 issues closed