Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.
安装
npx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-long-contextnpx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-long-context -a claude-code -gnpx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-long-context -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/nemo-mbridge-perf-moe-long-contextgh skill install NVIDIA/skills nemo-mbridge-perf-moe-long-contextgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/nemo-mbridge-perf-moe-long-context ~/.claude/skills/nemo-mbridge-perf-moe-long-context # Claude Code
cp -R /tmp/NVIDIA__skills/skills/nemo-mbridge-perf-moe-long-context ~/.agents/skills/nemo-mbridge-perf-moe-long-context # Codex, Cursor, Gemini CLI, Copilot, OpenCode