Update LLM support for llama.cpp and enhance configuration management

- Added support for `llamacpp-models.yaml` in `.gitignore` and implemented logic to copy it in `gpu-rent.ps1` and `gpu-rent.sh`.
- Enhanced CLI to prompt for llama.cpp model presets during setup and execution, improving user experience.
- Updated configuration handling to include `llamacpp_models_manifest` and related functions for managing llama.cpp models.
- Improved documentation in `cli.md` and `llm.md` to reflect changes in llama.cpp integration and model management.
- Refactored provisioning logic to handle llama.cpp model downloads and configurations effectively.

src/gpu_rent/setup_wizard.py

@@ -7,16 +7,21 @@ from collections.abc import Callable
 from pathlib import Path
 
 from gpu_rent.llm_runtime import (
+    LLAMACPP_PRESET_HELP,
     PRESET_HELP,
     append_vars_llm_runtime,
+    ensure_llamacpp_manifest_from_example,
     ensure_ollama_manifest_from_example,
     normalize_runtime,
+    write_llamacpp_models_preset,
     write_ollama_models_preset,
 )
 from gpu_rent.paths import (
     app_root,
     env_path,
     extensions_manifest_path,
+    llamacpp_models_example_path,
+    llamacpp_models_manifest_path,
     models_manifest_path,
     ollama_models_example_path,
     ollama_models_manifest_path,
@@ -59,6 +64,12 @@ def run_setup(
     _copy_if_missing(
         ollama_models_example_path(), ollama_models_manifest_path(), "ollama-models.yaml", log
     )
+    _copy_if_missing(
+        llamacpp_models_example_path(),
+        llamacpp_models_manifest_path(),
+        "llamacpp-models.yaml",
+        log,
+    )
 
     runtime = llm
     if runtime is None:
@@ -86,6 +97,22 @@ def run_setup(
         else:
             write_ollama_models_preset(ollama_models_manifest_path(), preset)
             log(f"ollama-models.yaml пресет={preset}")
+    elif runtime == "llamacpp":
+        preset = ollama_preset  # reuse --ollama-preset flag as generic LLM preset in setup
+        if preset is None and ask:
+            log(LLAMACPP_PRESET_HELP)
+            preset = ask(
+                "llama.cpp GGUF preset [recommended/light/stock/empty]",
+                "recommended",
+            )
+        if preset is None:
+            preset = "recommended"
+        if preset.strip().lower() in {"keep", "example", ""}:
+            ensure_llamacpp_manifest_from_example()
+            log("llamacpp-models.yaml из example")
+        else:
+            write_llamacpp_models_preset(llamacpp_models_manifest_path(), preset)
+            log(f"llamacpp-models.yaml пресет={preset}")
 
     do_wd = install_watchdog
     if do_wd is None and confirm: