Follows the homelab pattern: ironicbadger.docker_compose_generator v2 renders services/<host>/NN-<stack>/compose.yml templates into ~/docker/compose.yaml on the host. - 01-vllm: chat model, fixed --gpu-memory-utilization - 02-embeddings: second vLLM instance (--task embed) rather than a separate toolchain, so SM120 support only has to be solved once - 03-openwebui: Open WebUI + pgvector (not chroma — corpus size) - 99-network: shared bridge; leading comment keeps networks: top-level - pin docker_compose_generator to 2.0.1 — galaxy tags mix v1/v2 formats - group_vars: stack config incl. LDAP placeholders still to be filled The role only writes the compose file; starting the stack stays manual. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
42 lines
1.4 KiB
YAML
42 lines
1.4 KiB
YAML
---
|
|
# overrides of group_vars/all.yml
|
|
|
|
hostname: phy-srv-gpu01
|
|
|
|
# geerlingguy.docker
|
|
docker_users:
|
|
- "{{ main_username }}"
|
|
|
|
# ironicbadger.docker_compose_generator
|
|
# services/<docker_compose_hostname>/NN-<stack>/compose.yml next to run.yml
|
|
appdata_path: "/home/{{ main_username }}/appdata"
|
|
docker_compose_generator_output_path: "/home/{{ main_username }}/docker/"
|
|
docker_compose_hostname: phy-srv-gpu01
|
|
docker_compose_generator_uid: "{{ main_uid }}"
|
|
docker_compose_generator_gid: "{{ main_gid }}"
|
|
|
|
# --- LLM stack -------------------------------------------------------------
|
|
llm_dns_name: chat.phytron.local
|
|
|
|
# ⚠️ TODO: pin to a build verified on SM120 (Blackwell) before the first deploy
|
|
vllm_image: vllm/vllm-openai:latest
|
|
vllm_model: Qwen/Qwen3-32B-FP8
|
|
vllm_served_model_name: qwen3-32b
|
|
vllm_gpu_memory_utilization: "0.80"
|
|
vllm_max_model_len: "32768"
|
|
|
|
embedding_model: BAAI/bge-m3
|
|
embedding_model_name: bge-m3
|
|
embeddings_gpu_memory_utilization: "0.10"
|
|
|
|
openwebui_image: ghcr.io/open-webui/open-webui:main
|
|
pgvector_image: pgvector/pgvector:pg16
|
|
|
|
# --- AD/LDAP ---------------------------------------------------------------
|
|
# ⚠️ TODO: real bind DN / base DN from the customer; group llm_users is agreed
|
|
ldap_server_host: dc.phytron.local
|
|
ldap_server_port: "389"
|
|
ldap_bind_dn: "CN=svc-llm,OU=Service,DC=phytron,DC=local"
|
|
ldap_search_base: "DC=phytron,DC=local"
|
|
ldap_search_filter: "(&(objectClass=user)(memberOf=CN=llm_users,OU=Groups,DC=phytron,DC=local))"
|