SageSched: Intelligent LLM Request Scheduler with Workload Prediction — QoS-aware dual-queue scheduling for black-box LLM APIs (OpenAI/Azure/Doubao/Gemini)
-
Updated
May 18, 2026 - Python
SageSched: Intelligent LLM Request Scheduler with Workload Prediction — QoS-aware dual-queue scheduling for black-box LLM APIs (OpenAI/Azure/Doubao/Gemini)
Experimental pipeline for a simulation-based comparison of ML-driven auto-scaling policies (LSTM and Random Forest) against Kubernetes HPA, using the Alibaba Cluster Trace 2018 dataset. Published at UTP Student and Doctoral Scientific Session 2026.
Research paper and technical notes on the microservice ecosystem
Self-adaptive data layout for distribute joins
Add a description, image, and links to the workload-prediction topic page so that developers can more easily learn about it.
To associate your repository with the workload-prediction topic, visit your repo's landing page and select "manage topics."