Kubernetes operator and aggregated apiserver implementing the agent-sandbox standard: warm microVM pools, ~33 ms claims through the Kubernetes API, and fleet scale with etcd off the claim path.
-
Updated
Jul 27, 2026 - Go
#
warm-pool
Here are 3 public repositories matching this topic...
Phase-by-phase benchmark of LLM instance cold start on RTX 2070: weight loading, PCIe transfer, CUDA init, KV cache allocation, and JIT warmup — with pre-warming savings and extrapolation to 7B+ models.
benchmarking cuda inference pytorch cold-start autoscaling pcie kv-cache llm-serving warm-pool mlsystems startup-latency weight-loading
-
Updated
Jul 19, 2026 - Python
Zero-downtime deployments on AWS using Blue-Green Deployments, Rolling Deployments, Auto Scaling, Application Load Balancer, Lifecycle Hooks, and Warm Pools.
aws ec2 high-availability autoscaling lifecycle-hooks application-load-balancer blue-green-deployment cloud-engineering launch-template aws-project warm-pool rolling-deployment
-
Updated
Jun 29, 2026
Improve this page
Add a description, image, and links to the warm-pool topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the warm-pool topic, visit your repo's landing page and select "manage topics."