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.

gpu-rent.vars.example

@@ -31,59 +31,24 @@
 # Подробнее: docs/llm.md
 # ---------------------------------------------------------------------------
 
-# --- A) Default: SwarmUI + llama.cpp (auto: CUDA если nvcc на VM, иначе Vulkan) ---
-# LLM_RUNTIME=llamacpp
+# --- A) Default: SwarmUI + Ollama ---
+# LLM_RUNTIME=ollama
 # ENABLE_SWARMUI=true
-# LLAMACPP_TAG=b10545
-# LLAMACPP_BACKEND=auto
+# OLLAMA_LOCAL_PORT=17811
 
 # --- B) Только LLM, без SwarmUI ---
 # WORKLOAD=llm
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_TAG=b10545
+# LLM_RUNTIME=ollama
 
-# --- C) Явно CUDA (и снести старый Vulkan-бинарь) ---
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_TAG=b10545
-# LLAMACPP_BACKEND=cuda
-# LLAMACPP_FORCE_REINSTALL=1
-
-# --- C2) Явно быстрый Vulkan, без compile ---
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_BACKEND=vulkan
-# LLAMACPP_BUILD_CUDA=0
-
-# --- D) Свой бинарь / pin URL (supply-chain) ---
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_ASSET_URL=https://github.com/ggml-org/llama.cpp/releases/download/b10545/llama-b10545-bin-ubuntu-vulkan-x64.tar.gz
-# LLAMACPP_SHA256=<sha256 архива>
-# LLAMACPP_FORCE_REINSTALL=1
-
-# --- E) Делим 4090 со SwarmUI: меньше слоёв / короче контекст ---
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_NGL=40
-# LLAMACPP_CTX=4096
-# LLAMACPP_EXTRA_ARGS=--flash-attn on
-
-# --- F) Длинный контекст / почти весь VRAM под LLM (llm-only) ---
-# WORKLOAD=llm
-# LLM_RUNTIME=llamacpp
-# LLAMACPP_NGL=99
-# LLAMACPP_CTX=32768
-# LLAMACPP_EXTRA_ARGS=--parallel 1
-
-# --- G) Ollama вместо llama.cpp + pin версии ---
+# --- C) Pin версии Ollama (supply-chain) ---
 # LLM_RUNTIME=ollama
 # OLLAMA_VERSION=0.6.5
 # OLLAMA_SHA256=<sha256 of ollama-linux-amd64.tgz>
-# OLLAMA_LOCAL_PORT=17811
 
-# --- H) Выключить LLM (гасит unit’ы на следующем up) ---
+# --- D) Выключить LLM (гасит unit’ы на следующем up) ---
 # LLM_RUNTIME=none
 
-# Порты туннеля (localhost):
+# Порт туннеля (localhost):
 # OLLAMA_LOCAL_PORT=17811
-# LLAMACPP_LOCAL_PORT=17812
-# Свой путь к манифесту GGUF/pull:
-# LLAMACPP_MODELS_MANIFEST=
+# Свой путь к манифесту pull:
 # OLLAMA_MODELS_MANIFEST=