376  text-generation-webui - configuration reference

377 text-generation-webui — configuration reference

Configuration surfaces for text-generation-webui (safety class: safe; category: o-04-local-llm-inference-labs) — detected from the upstream documentation at generation time (7 config-surface markers). The invocation reference stays on the main tool page.

377.1 Configuration files

Path

Context

nvidia/docker-compose.yml

For NVIDIA GPU: ln -s docker/{nvidia/Dockerfile,nvidia/docker-compose.yml,.dockerignore} . For AMD GPU: ln -s docker/{ | |amd/docker-compose.yml| nore} . For AMD GPU: ln -s docker/{amd/Dockerfile,amd/docker-compose.yml,.dockerignore} . For Intel GPU: ln -s docker/{i | |intel/docker-compose.yml| } . For Intel GPU: ln -s docker/{intel/Dockerfile,intel/docker-compose.yml,.dockerignore} . For CPU only ln -s docker/{c | |cpu/docker-compose.yml| nore} . For CPU only ln -s docker/{cpu/Dockerfile,cpu/docker-compose.yml,.dockerignore} . cp docker/.env.example .env #C | |user_data/settings-template.yaml| fault interface settings from this yaml file. See user_data/settings-template.yaml for an example. If you create a file | |user_data/settings.yaml`

377.2 Environment variables

Variable	Upstream context
USER_DATA_DIR	st

Names extracted heuristically from upstream docs — verify each against the tool’s own docs before use.

377.3 Sample configuration (upstream)

textgen
└── user_data
    └── models
        └── Qwen_Qwen3-8B
            ├── config.json
            ├── generation_config.json
            ├── model-00001-of-00004.safetensors
            ├── ...
            ├── tokenizer_config.json
            └── tokenizer.json

For NVIDIA GPU:
ln -s docker/{nvidia/Dockerfile,nvidia/docker-compose.yml,.dockerignore} .
For AMD GPU:
ln -s docker/{amd/Dockerfile,amd/docker-compose.yml,.dockerignore} .
For Intel GPU:
ln -s docker/{intel/Dockerfile,intel/docker-compose.yml,.dockerignore} .
For CPU only
ln -s docker/{cpu/Dockerfile,cpu/docker-compose.yml,.dockerignore} .
cp docker/.env.example .env
#Create logs/cache dir :
mkdir -p user_data/logs user_data/cache
# Edit .env and set:
#   TORCH_CUDA_ARCH_LIST based on your GPU model
#   APP_RUNTIME_GID      your host user's group id (run `id -g` in a terminal)
#   BUILD_EXTENIONS      optionally add comma separated list of extensions to build
# Edit user_data/CMD_FLAGS.txt and add in it the options you want to execute (like --listen --cpu)
#
docker compose up --build

---

ref: pin - verified 2026-10-14