refactor: rename docker-compose.gpu.yaml to compose.yaml
Simplified compose file naming to follow Docker Compose best practices: - Renamed docker-compose.gpu.yaml to compose.yaml - Updated all references in documentation files (README.md, DEPLOYMENT.md, GPU_DEPLOYMENT_LOG.md, RUNPOD_TEMPLATE.md) - Updated references in scripts (prepare-template.sh) This change enables simpler command syntax: - Before: docker compose -f docker-compose.gpu.yaml up -d orchestrator - After: docker compose up -d orchestrator Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -23,7 +23,7 @@ If you've already created a RunPod template:
|
||||
1. Deploy pod from template in RunPod dashboard
|
||||
2. SSH to the pod
|
||||
3. Create `.env` file with your credentials
|
||||
4. Start orchestrator: `docker compose -f docker-compose.gpu.yaml up -d orchestrator`
|
||||
4. Start orchestrator: `docker compose -f compose.yaml up -d orchestrator`
|
||||
|
||||
**See**: [RUNPOD_TEMPLATE.md](RUNPOD_TEMPLATE.md) for template usage instructions.
|
||||
|
||||
@@ -107,7 +107,7 @@ models:
|
||||
endpoint: /v1/chat/completions
|
||||
```
|
||||
|
||||
Then add the Docker service to `docker-compose.gpu.yaml` and restart the orchestrator.
|
||||
Then add the Docker service to `compose.yaml` and restart the orchestrator.
|
||||
|
||||
**See**: [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md#adding-new-models) for complete instructions.
|
||||
|
||||
|
||||
@@ -94,7 +94,7 @@ ssh gpu-pivoine
|
||||
cd /workspace/ai/
|
||||
|
||||
# Start orchestrator (always running)
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
|
||||
# Orchestrator will automatically manage model services as needed
|
||||
```
|
||||
@@ -217,7 +217,7 @@ models:
|
||||
### Step 2: Add Docker Service
|
||||
|
||||
```yaml
|
||||
# Add to ai/docker-compose.gpu.yaml
|
||||
# Add to ai/compose.yaml
|
||||
services:
|
||||
vllm-llama:
|
||||
build: ./vllm
|
||||
@@ -245,7 +245,7 @@ services:
|
||||
```bash
|
||||
ssh gpu-pivoine
|
||||
cd /workspace/ai/
|
||||
docker compose -f docker-compose.gpu.yaml restart orchestrator
|
||||
docker compose -f compose.yaml restart orchestrator
|
||||
```
|
||||
|
||||
**That's it!** The orchestrator automatically detects the new model.
|
||||
@@ -256,13 +256,13 @@ docker compose -f docker-compose.gpu.yaml restart orchestrator
|
||||
|
||||
```bash
|
||||
# Start orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
|
||||
# View orchestrator logs
|
||||
docker logs -f ai_orchestrator
|
||||
|
||||
# Restart orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml restart orchestrator
|
||||
docker compose -f compose.yaml restart orchestrator
|
||||
|
||||
# Check active model
|
||||
curl http://100.100.108.13:9000/health
|
||||
@@ -287,10 +287,10 @@ curl http://100.100.108.13:9000/health | jq '.current_model'
|
||||
|
||||
```bash
|
||||
# Manually start a specific model (bypassing orchestrator)
|
||||
docker compose -f docker-compose.gpu.yaml --profile text up -d vllm-qwen
|
||||
docker compose -f compose.yaml --profile text up -d vllm-qwen
|
||||
|
||||
# Stop a model
|
||||
docker compose -f docker-compose.gpu.yaml stop vllm-qwen
|
||||
docker compose -f compose.yaml stop vllm-qwen
|
||||
|
||||
# View model logs
|
||||
docker logs -f ai_vllm-qwen_1
|
||||
@@ -337,10 +337,10 @@ docker logs -f ai_musicgen_1
|
||||
docker logs ai_orchestrator
|
||||
|
||||
# Check if model service exists
|
||||
docker compose -f docker-compose.gpu.yaml config | grep -A 10 "vllm-qwen"
|
||||
docker compose -f compose.yaml config | grep -A 10 "vllm-qwen"
|
||||
|
||||
# Manually test model service
|
||||
docker compose -f docker-compose.gpu.yaml --profile text up -d vllm-qwen
|
||||
docker compose -f compose.yaml --profile text up -d vllm-qwen
|
||||
curl http://localhost:8001/health
|
||||
```
|
||||
|
||||
@@ -354,8 +354,8 @@ ls -l /var/run/docker.sock
|
||||
sudo systemctl restart docker
|
||||
|
||||
# Rebuild orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml build orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml build orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
```
|
||||
|
||||
### Model Switching Too Slow
|
||||
@@ -376,7 +376,7 @@ docker run --rm -it --gpus all \
|
||||
|
||||
```
|
||||
ai/
|
||||
├── docker-compose.gpu.yaml # Main orchestration file
|
||||
├── compose.yaml # Main orchestration file
|
||||
├── .env.example # Environment template
|
||||
├── README.md # This file
|
||||
│
|
||||
|
||||
@@ -260,7 +260,7 @@ models:
|
||||
### Deployment Changes
|
||||
|
||||
#### Docker Compose Structure
|
||||
- **File**: `docker-compose.gpu.yaml`
|
||||
- **File**: `compose.yaml`
|
||||
- **Services**: 4 total (1 orchestrator + 3 models)
|
||||
- **Profiles**: `text`, `image`, `audio` (orchestrator manages activation)
|
||||
- **Restart Policy**: `no` for models (orchestrator controls lifecycle)
|
||||
@@ -319,7 +319,7 @@ ssh gpu-pivoine
|
||||
cd /workspace/ai/
|
||||
|
||||
# Start orchestrator (manages everything)
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
|
||||
# Check status
|
||||
curl http://100.100.108.13:9000/health
|
||||
|
||||
@@ -116,14 +116,14 @@ ls -lh /workspace/musicgen/models/
|
||||
|
||||
# Test orchestrator starts
|
||||
cd /workspace/ai
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
docker logs ai_orchestrator
|
||||
|
||||
# Test model loading (should be fast since models are cached)
|
||||
curl http://localhost:9000/health
|
||||
|
||||
# Stop orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml down
|
||||
docker compose -f compose.yaml down
|
||||
```
|
||||
|
||||
### Step 4: Clean Up Before Saving
|
||||
@@ -215,7 +215,7 @@ EOF
|
||||
tailscale up --authkey=<YOUR_TAILSCALE_KEY>
|
||||
|
||||
# Start orchestrator (models already cached, starts in seconds!)
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
|
||||
# Verify
|
||||
curl http://localhost:9000/health
|
||||
@@ -295,12 +295,12 @@ docker compose --profile audio up -d musicgen
|
||||
|
||||
```bash
|
||||
# Build images one at a time
|
||||
docker compose -f docker-compose.gpu.yaml build orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml build vllm-qwen
|
||||
docker compose -f docker-compose.gpu.yaml build musicgen
|
||||
docker compose -f compose.yaml build orchestrator
|
||||
docker compose -f compose.yaml build vllm-qwen
|
||||
docker compose -f compose.yaml build musicgen
|
||||
|
||||
# Check build logs for errors
|
||||
docker compose -f docker-compose.gpu.yaml build --no-cache --progress=plain orchestrator
|
||||
docker compose -f compose.yaml build --no-cache --progress=plain orchestrator
|
||||
```
|
||||
|
||||
### Tailscale Won't Install
|
||||
|
||||
@@ -118,15 +118,15 @@ build_docker_images() {
|
||||
|
||||
# Build orchestrator
|
||||
log_info "Building orchestrator..."
|
||||
docker compose -f docker-compose.gpu.yaml build orchestrator
|
||||
docker compose -f compose.yaml build orchestrator
|
||||
|
||||
# Build vLLM
|
||||
log_info "Building vLLM..."
|
||||
docker compose -f docker-compose.gpu.yaml build vllm-qwen
|
||||
docker compose -f compose.yaml build vllm-qwen
|
||||
|
||||
# Build MusicGen
|
||||
log_info "Building MusicGen..."
|
||||
docker compose -f docker-compose.gpu.yaml build musicgen
|
||||
docker compose -f compose.yaml build musicgen
|
||||
|
||||
# Pull Flux image (pre-built)
|
||||
log_info "Pulling Flux.1 image..."
|
||||
@@ -196,7 +196,7 @@ validate_installation() {
|
||||
|
||||
# Start orchestrator
|
||||
log_info "Starting orchestrator for validation..."
|
||||
docker compose -f docker-compose.gpu.yaml up -d orchestrator
|
||||
docker compose -f compose.yaml up -d orchestrator
|
||||
|
||||
sleep 10
|
||||
|
||||
@@ -217,7 +217,7 @@ validate_installation() {
|
||||
fi
|
||||
|
||||
# Stop orchestrator
|
||||
docker compose -f docker-compose.gpu.yaml down
|
||||
docker compose -f compose.yaml down
|
||||
|
||||
log_success "Validation passed"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user