[WIP] Fix runtime and setup failures in NPU-STACK

[Copilot]

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

Original prompt

User wants direct repository corrections they can git pull for chainchopper/NPU-STACK on main. Implement and open a PR that fixes the reported runtime/setup failures quickly.

Context from user logs:

• Windows run-all.bat error: 'Frontend:' is not recognized as an internal or external command.
• Docker backend build fails because llama.cpp Makefile build is deprecated and now requires CMake.

Required fixes:

1. Fix run-all.bat so status text is echoed correctly and not interpreted as commands; ensure backend/frontend launch behavior works on Windows cmd.
2. Update Docker backend build stage(s) replacing make llama.cpp build with CMake-based build that produces required tools (llama-quantize, llama-gguf-split, llama-imatrix, llama-cli, llama-server, llama-export-lora or correct upstream equivalents).
3. Keep changes minimal and safe so user can pull and retry immediately.
4. Update README/setup docs briefly if command/build behavior changed.

Acceptance criteria:

• run-all.bat runs without Frontend: command error.
• docker compose up --build no longer fails at deprecated llama.cpp make step.
• PR created against main in chainchopper/NPU-STACK with concise change summary and verification steps.

This pull request was created from Copilot chat.

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

[Copilot]

Copilot wasn't able to review any files in this pull request.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.