cuda-checkpoint

Here are 2 public repositories matching this topic...

ai-dynamo / snapshot

Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scratch. Kubernetes-native checkpoint & restore that runs alongside your existing stack.

kubernetes gpu inference cold-start criu checkpoint-restore cuda-checkpoint

Updated Sep 19, 2026
Go

gbram1 / embers

Star

Serverless-GPU LLM serving: scale-to-zero with fast GPU snapshot/restore (cuda-checkpoint), multi-tenant packing, and an OpenAI-compatible API — built on vLLM.

serverless gpu cuda lora autoscaling scale-to-zero openai-api llm-serving vllm llm-inference snapshot-restore cuda-checkpoint

Updated Jul 5, 2026
Python

Add this topic to your repo

To associate your repository with the cuda-checkpoint topic, visit your repo's landing page and select "manage topics."

Learn more