mirror of
https://github.com/furyhawk/home_stack.git
synced 2026-07-21 18:26:54 +00:00
furyhawk
9d090e937d
- Updated .gitignore to include new model directories. - Removed version specification from existing docker-compose.yml for llama-cpp-server. - Created new docker-compose.yml for ai_stack/llamacpp.server with GPU support and environment configurations. - Added Gemma4_(E2B)_Vision.ipynb notebook for data preparation, training, and inference of the Gemma 4 model.
33 lines
899 B
YAML
33 lines
899 B
YAML
services:
|
|
llama-cpp-server:
|
|
build: .
|
|
image: localhost/llama-cpp-server:latest
|
|
ports:
|
|
- "8080:8080" # Map host port 8080 to container port 8080
|
|
volumes:
|
|
- ./models:/models # Mount a local directory for models
|
|
container_name: llama-cpp-server
|
|
environment:
|
|
- LLAMA_ARG_HOST=0.0.0.0
|
|
- LLAMA_ARG_PORT=8080
|
|
restart: unless-stopped
|
|
command: [
|
|
"llama-server",
|
|
"--model", "/models/DeepSeek-R1-0528-Qwen3-8B-UD-Q4_K_XL.gguf",
|
|
"--host", "0.0.0.0",
|
|
"--port", "8080",
|
|
"--ctx-size", "32768",
|
|
"--threads", "4",
|
|
"--batch-size", "512",
|
|
"--cont-batching",
|
|
"--parallel", "2",
|
|
"--flash-attn"
|
|
]
|
|
# Uncomment for GPU support
|
|
# deploy:
|
|
# resources:
|
|
# reservations:
|
|
# devices:
|
|
# - driver: nvidia
|
|
# count: all
|
|
# capabilities: [gpu] |