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.

env.example

@@ -38,29 +38,18 @@ AUTOCOMPLETE_GITHUB_REF=main
 AUTOCOMPLETE_FILENAME=danbooru.csv
 
 SWARMUI_LOCAL_PORT=17801
-# Optional LLM beside SwarmUI: none | ollama | llamacpp (setup / --ollama / --llamacpp)
+# Optional LLM beside SwarmUI: none | ollama (setup / --ollama / --llm ollama)
 # ENABLE_SWARMUI=true
-# WORKLOAD=llm          # llm-only (no SwarmUI); requires LLM_RUNTIME≠none
+# WORKLOAD=llm          # llm-only (no SwarmUI); requires LLM_RUNTIME=ollama
 LLM_RUNTIME=none
 OLLAMA_LOCAL_PORT=17811
-LLAMACPP_LOCAL_PORT=17812
 # OLLAMA_MODELS_MANIFEST=
-# LLAMACPP_MODELS_MANIFEST=
-# Pin / тонкая настройка LLM (несecреты; удобнее в gpu-rent.vars — см. кейсы A–H):
-# LLAMACPP_TAG=b10545
-# LLAMACPP_BACKEND=auto
-# LLAMACPP_BUILD_CUDA=1
-# LLAMACPP_FORCE_REINSTALL=1
-# LLAMACPP_ASSET_URL=
-# LLAMACPP_SHA256=
-# LLAMACPP_NGL=40
-# LLAMACPP_CTX=4096
-# LLAMACPP_EXTRA_ARGS=--flash-attn on
+# Pin Ollama (несecреты; удобнее в gpu-rent.vars):
 # OLLAMA_VERSION=0.6.5
 # OLLAMA_SHA256=
 # CIVITAI_API_TOKEN=
 # CIVITAI_API_HOST=civitai.red
-# Hugging Face (GGUF / gated HF URLs / capture fallback metadata):
+# Hugging Face (HF URLs in models.yaml / capture fallback metadata):
 # HF_TOKEN=   # or HUGGING_FACE_HUB_TOKEN — https://huggingface.co/settings/tokens
 # git pull SwarmUI + extensions on each up (default true). CLI: --no-update
 UPDATE_GIT=true