High-throughput LLM inference on NVIDIA GPUs.
安装
npx skills add NousResearch/hermes-agent --skill tensorrt-llmnpx skills add NousResearch/hermes-agent --skill tensorrt-llm -a claude-code -gnpx skills add NousResearch/hermes-agent --skill tensorrt-llm -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/tensorrt-llmgh skill install NousResearch/hermes-agent tensorrt-llmgit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/tensorrt-llm ~/.claude/skills/tensorrt-llm # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/tensorrt-llm ~/.agents/skills/tensorrt-llm # Codex, Cursor, Gemini CLI, Copilot, OpenCode