Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
安装
npx skills add davila7/claude-code-templates --skill pytorch-fsdpnpx skills add davila7/claude-code-templates --skill pytorch-fsdp -a claude-code -gnpx skills add davila7/claude-code-templates --skill pytorch-fsdp -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/distributed-training-pytorch-fsdpgh skill install davila7/claude-code-templates pytorch-fsdpgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/distributed-training-pytorch-fsdp ~/.claude/skills/pytorch-fsdp # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/distributed-training-pytorch-fsdp ~/.agents/skills/pytorch-fsdp # Codex, Cursor, Gemini CLI, Copilot, OpenCode