pi-mono/packages/pods/README.md — installation, pod management, model commands, GPU multi-assignment, and pre-defined models.
pi-mono/packages/pods/src/ — CLI commands implementation if needing deeper args validation.
Invariants
Auto-assignment: When running multiple models on the same pod, pi automatically assigns them to different GPUs.
Parameter Ignorance: When passing custom vLLM args with --vllm, the default CLI shortcuts for --memory, --context, and --gpus are ignored.
Workflows
Setup Pod: Use pi pods setup <name> "<ssh>" along with --mount for shared NFS storage (DataCrunch) or network volumes (RunPod).
Start Pre-defined Model: Use pi start <model> --name <name> for known agentic models (Qwen, GLM, GPT-OSS). The tool calling parsers are automatically configured.
Custom vLLM Args: Pass specific settings (e.g. tensor parallelism) using --vllm --tensor-parallel-size <N>.
Anti-patterns
Do not manually construct tool-calling parsers for pre-defined models like Qwen or GLM; pi configures hermes or glm4_moe automatically.
Do not assume models are downloaded redundantly on DataCrunch; emphasize the NFS shared models path (/mnt/hf-models).
1---2name: pi-pods3description: Pi Pods4---56# Pi Pods78## Grounding9101. `pi-mono/packages/pods/README.md` — installation, pod management, model commands, GPU multi-assignment, and pre-defined models.112. `pi-mono/packages/pods/src/` — CLI commands implementation if needing deeper args validation.1213## Invariants1415- **Auto-assignment**: When running multiple models on the same pod, `pi` automatically assigns them to different GPUs.16- **Parameter Ignorance**: When passing custom vLLM args with `--vllm`, the default CLI shortcuts for `--memory`, `--context`, and `--gpus` are ignored.1718## Workflows1920- **Setup Pod**: Use `pi pods setup <name> "<ssh>"` along with `--mount` for shared NFS storage (DataCrunch) or network volumes (RunPod).21- **Start Pre-defined Model**: Use `pi start <model> --name <name>` for known agentic models (Qwen, GLM, GPT-OSS). The tool calling parsers are automatically configured.22- **Custom vLLM Args**: Pass specific settings (e.g. tensor parallelism) using `--vllm --tensor-parallel-size <N>`.2324## Anti-patterns2526- Do not manually construct tool-calling parsers for pre-defined models like Qwen or GLM; `pi` configures `hermes` or `glm4_moe` automatically.27- Do not assume models are downloaded redundantly on DataCrunch; emphasize the NFS shared models path (`/mnt/hf-models`).
Run npx skillmds@latest add romiluz13/pi-pods in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Pi Pods It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
romiluz13 (@romiluz13) published this skill. Their other Agent Skills are listed on their SkillMD profile.
romiluz13