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/access_card.py

@@ -71,19 +71,6 @@ def collect_access_links(cfg: Config, *, tunneled: bool) -> list[AccessLink]:
                     ),
                 ]
             )
-        elif runtime == "llamacpp":
-            p = cfg.llamacpp_local_port
-            links.extend(
-                [
-                    AccessLink("llama.cpp", f"http://127.0.0.1:{p}", "OpenAI-compatible"),
-                    AccessLink(
-                        "OpenAI /v1",
-                        f"http://127.0.0.1:{p}/v1/chat/completions",
-                        "chat completions",
-                    ),
-                    AccessLink("Models", f"http://127.0.0.1:{p}/v1/models", "list"),
-                ]
-            )
         if not links:
             links.append(
                 AccessLink(
@@ -138,7 +125,7 @@ def render_access_panel(
     cmds.add_column(style="dim", no_wrap=True)
     cmds.add_column()
     cmds.add_row("открыть UI", "gpu-rent open")
-    if resolve_llm_runtime(cfg) in {"ollama", "llamacpp"}:
+    if resolve_llm_runtime(cfg) == "ollama":
         cmds.add_row("открыть LLM", "gpu-rent open --llm")
     cmds.add_row("hold killer", "gpu-rent hold")
     cmds.add_row("стоп GPU", "gpu-rent stop")