Pinned Loading

1. An open and reliable container runtime

   Go 20.4k 3.8k

2. Production-Grade Container Scheduling and Management

   Go 121k 42.6k

3. Forked from Project-HAMi/HAMi

   OpenAIOS vGPU scheduler for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory.

   Go

4. Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python

5. Forked from limstash/mpu

   A shim driver allows in-docker nvidia-smi showing correct process list without modify anything

   C 4 1