cosmos3-setup

작성자: nvidia

사용자가 Cosmos3 설치, 환경 설정, 체크포인트 다운로드 및 검증 과정을 안내받을 수 있도록 돕습니다. 사용자가 "cosmos3 설치 방법", "어떻게…"라고 물을 때 사용하세요.

npx skills add https://github.com/nvidia/cosmos-framework --skill cosmos3-setup

Cosmos3 Setup

When to use this skill

  • Use when a user wants to install Cosmos3 or set up a development environment
  • Use when a user asks about system requirements, CUDA versions, or GPU compatibility
  • Use when a user needs to download model checkpoints or configure HuggingFace auth
  • Use when a user wants to run Cosmos3 inside a Docker container or NGC container
  • For errors during setup, hand off to the cosmos3-env-troubleshoot skill

Path convention

All paths below are relative to the cosmos3 package root (../../../ from this skill file). All uv run / python commands should also be run from there.

Where to find answers

The canonical setup reference is docs/setup.md. The README (README.md § Setup) has the shortest quickstart.

User questionGo to
What are the system requirements?docs/setup.md § System Requirements
How do I install with uv? (sync, pip venv, pip system)docs/setup.md § Virtual Environment
How do I install with Docker?docs/setup.md § Docker Container
Custom torch/CUDA versions or attention backends?docs/setup.md § Advanced
Which CUDA version? (cu130 vs cu128)docs/setup.md § CUDA Variants, docs/faq.md § Which CUDA version?
How do I download checkpoints?docs/setup.md § Downloading Base Checkpoints
NGC container issues?docs/setup.md § PyTorch Import Issue
Any installation error../cosmos3-env-troubleshoot/SKILL.md

Setup steps at a glance

  1. Clone the repository and cd into the project root (the directory containing pyproject.toml)
  2. System deps: sudo apt-get install -y --no-install-recommends curl ffmpeg git-lfs libx11-dev tree wget
  3. Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh && source $HOME/.local/bin/env
  4. Install package: uv sync --all-extras --group=cu130-train && source .venv/bin/activate && export LD_LIBRARY_PATH= (use cu128-train on older drivers; the inference-only cu130 / cu128 groups omit the training extras)
  5. Checkpoints: auto-downloaded during inference; requires HuggingFace auth (see docs)
  6. Verify: uv run --all-extras --group=cu130-train python -c "import cosmos_framework; print('ok')"

Things not obvious from the docs

  • NGC container caveat: you must run export LD_LIBRARY_PATH='' before any Python imports when inside an NGC PyTorch container. Easy to miss.
  • CUDA version alignment: the major CUDA version from nvidia-smi must match torch.version.cuda. Mismatches cause cryptic shared-library errors.
  • HF_HOME: controls where checkpoints are cached (default: ~/.cache/huggingface). Set this if disk space is tight or you want a shared cache.
  • Conflicting env vars: stale HF_TOKEN or HUGGING_FACE_HUB_TOKEN env vars can silently override CLI auth. Check with printenv | grep HF_.

Related skills

SkillWhen to use
../cosmos3-inference/SKILL.mdRunning inference after setup is complete
../cosmos3-codebase-nav/SKILL.mdFinding files, parameters, and configs in code
../cosmos3-env-troubleshoot/SKILL.mdDebugging environment and runtime errors

nvidia의 다른 스킬

fhir-basics
nvidia
에이전트에게 FHIR R4 API의 작동 방식, 사용 가능한 리소스, 검색 매개변수를 사용한 쿼리 방법, 모든 응답 형식을 올바르게 파싱하는 방법을 가르칩니다…
compileiq-validate-result
nvidia
검색이 완료된 후, 속도 향상을 청구하거나 ACF를 발송하기 전에 사용합니다. dump_results CSV를 로드하고, 상위 K개 후보(단일 목표)를 추출합니다…
changelog-audit
nvidia
릴리스 전에 Warp CHANGELOG.md를 감사합니다: 누락된 항목 복구, 사용자 영향별 정렬, 항목 언어 다듬기, 줄 바꿈, (릴리스 브랜치 모드) 비교 업데이트…
dgx-diagnose
nvidia
일반적인 DGX Station GB300 문제 진단 — CUDA 충돌, 잘못된 GPU 타겟팅, vLLM/SGLang 컨테이너 버그, MIG 상태 문제, NVLink/Fabric Manager 오류,…
aicr-managing-openvex
nvidia
Use when adding, updating, or removing CVE/GHSA suppressions in `.openvex.json` — the OpenVEX document consumed by the daily image vulnerability scan workflow.…
aicr-creating-slide-decks
nvidia
기술 개념이나 워크플로우에 대한 독립형 HTML 슬라이드 덱 또는 시각적 발표 자료(예: demos/*.html)를 만들 때 사용하세요. 전체 화면으로 표시하거나…
aicr-creating-guided-demos
nvidia
대화형 안내 데모 스크립트(demos/*.sh)를 라이브 또는 자기 주도 방식으로 Frame → Tell → Show → Close 패턴에 따라 구조화한다. "데모 스크립트", "안내…"와 같은 표현에 반응한다.
aicr-analyzing-snapshots
nvidia
AICR 스냅샷 YAML 파일을 분석하거나, 클러스터 상태를 검토하거나, 공급자 특성을 비교하거나, GPU/네트워크 토폴로지 인사이트를 추출할 때 사용합니다...