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/manifests.py

@@ -45,7 +45,7 @@ class ModelEntry:
     url: str | None
 
 
-VALID_REQUIRES = frozenset({"none", "ollama", "llamacpp", "any-llm"})
+VALID_REQUIRES = frozenset({"none", "ollama", "any-llm"})
 
 
 @dataclass
@@ -107,7 +107,7 @@ def normalize_requires(value: object | None) -> str:
     if raw in VALID_REQUIRES:
         return raw
     raise ConfigError(
-        f"requires={value!r}: жду none|ollama|llamacpp|any-llm"
+        f"requires={value!r}: жду none|ollama|any-llm"
     )
 
 
@@ -118,7 +118,7 @@ def repo_matches_runtime(repo: GitRepo, llm_runtime: str) -> bool:
     if req == "none":
         return True
     if req == "any-llm":
-        return runtime in {"ollama", "llamacpp"}
+        return runtime == "ollama"
     return runtime == req