Refactor LLM configuration to remove llamacpp support

- Removed references to llamacpp from configuration files, scripts, and documentation, streamlining the LLM setup process to focus solely on Ollama.
- Updated environment variables and paths to eliminate llamacpp-related entries, ensuring clarity in the configuration.
- Adjusted CLI commands and help messages to reflect the removal of llamacpp, enhancing user experience and reducing confusion.
- Revised documentation to provide clear guidance on using Ollama exclusively, including updates to setup instructions and runtime options.

src/gpu_rent/doctor.py

@@ -282,7 +282,6 @@ def _civitai(cfg: Config, checks: list[Check]) -> None:
 
 def _huggingface(cfg: Config, checks: list[Check]) -> None:
     from gpu_rent.huggingface import is_huggingface_url, probe_whoami
-    from gpu_rent.llm_runtime import normalize_runtime, parse_llamacpp_models
     from gpu_rent.manifests import parse_models
 
     needs_hf = False
@@ -293,14 +292,6 @@ def _huggingface(cfg: Config, checks: list[Check]) -> None:
                 break
     except Exception:
         pass
-    try:
-        if normalize_runtime(cfg.llm_runtime) == "llamacpp":
-            for e in parse_llamacpp_models(cfg.llamacpp_models_manifest):
-                if e.url and is_huggingface_url(e.url):
-                    needs_hf = True
-                    break
-    except Exception:
-        pass
 
     if not cfg.hf_token:
         checks.append(
@@ -309,7 +300,7 @@ def _huggingface(cfg: Config, checks: list[Check]) -> None:
                 True,
                 False,
                 (
-                    "HF_TOKEN нет — gated GGUF / HF в models.yaml дадут 401. "
+                    "HF_TOKEN нет — gated HF URL в models.yaml дадут 401. "
                     "https://huggingface.co/settings/tokens"
                     if needs_hf
                     else "токена нет (опционально для HF URL / capture fallback)"