Manage RKLLama model lifecycle on RK3588 NPUs with node pinning and explicit unload/load workflows.
npx skills add https://github.com/gilesknap/tpi-k3s-ansible --skill rkllama
Please help me install this Agent Skill. Skill: rkllama Source: https://github.com/gilesknap/tpi-k3s-ansible/tree/main/.claude/skills/rkllama Command: npx skills add https://github.com/gilesknap/tpi-k3s-ansible --skill rkllama
RKLLama provides reliable operations for RKLLama on RK3588 NPUs with node pinning, clear model lifecycle management, and visibility into silent-failure modes of rkllama_client pull.
Inspect the current RKLLama deployment and unload any active model to prepare for a new load.
High-intent search queries and answers about installing and using this skill.
You can manage the LLM lifecycle on an RK3588 NPU by using explicit unload and load workflows, ensuring a strict one-model-per-NPU constraint to switch models safely within your Kubernetes deployment.
Pinning a Kubernetes node for RKLLama ensures reliable operations by dedicating specific hardware, such as node04, to run the RKLLama workload and manage its per-node model state.
Yes, you can use rkllama_client via known in-pod command paths to pull and load models, utilizing host-side wrappers and NFS-backed model storage directories for reliable access.
Silent failures during a pull or load often occur when the one-model-per-NPU constraint is violated; explicitly unloading the active model before loading a new one resolves this issue.
Deploying RK3588 NPU models with NFS storage requires adhering to model directory conventions, applying strict one-model-per-NPU limits, and configuring appropriate quant settings for the hardware envelope.
sigridjinethProvisions a local Kubernetes lab environment with Vagrant and VirtualBox for Kubespray deployments.
ascend-ai-codingServe OpenAI-compatible LLM inference on Huawei Ascend NPUs.
DevMHOneMonitor provider health, circuit-breaker states, and latency metrics in real time.
ever-oliDeploy and manage vLLM servers for high-throughput LLM inference.
