Results for "oci"

Checkpoint/restore for vLLM that packages a warmed-up engine (processes, GPU state with CUDA graphs, processed weights; 1–8 GPUs on one node) as an OCI artifact and restores it in seconds on hosts with the same GPUs and driver branch.

Container-centric tool for simplifying local AI model serving. Automatically detects GPUs, pulls optimized container images, and runs models securely in rootless containers with enterprise-grade isolation.

CNCF open source DevOps tool for packaging, versioning, and securely sharing AI/ML models, datasets, code, and configuration. Packages everything into OCI artifacts stored in existing container registries. Apache 2.0 licensed.

Fast, local-first microVM runtime and library for isolated execution of AI agents and untrusted workloads. Apache 2.0 licensed.

Kubernetes operator for LLM serving with GPU scheduling and model lifecycle management across vLLM, SGLang, and TensorRT-LLM.

Open-source AI engine running LLMs, vision, voice, image, and video models on any hardware. Self-hosted OpenAI-compatible API. MIT licensed.

Local social-media research agent that uses TypeSafe Jev to select bounded socai CLI browser operations for Instagram, TikTok, and LinkedIn, streams captured evidence, and generates cited reports. MIT licensed.