Add AGENTS.md, deploy script, update README with service status and file locations
This commit is contained in:
Frank
@@ -0,0 +1,98 @@
|
||||
# vLLM Scripts — Agent Instructions
|
||||
|
||||
## Project Overview
|
||||
Scripts for running large language models via vLLM on two local machines:
|
||||
- **dankserver**: NVIDIA GPU + System RAM (frank-default-small)
|
||||
- **dankclaw**: AMD Strix Halo Shared Memory (frank-default-large)
|
||||
|
||||
## Directory Structure
|
||||
```
|
||||
vllmScripts/
|
||||
├── AGENTS.md # This file — agent instructions
|
||||
├── README.md # Human-readable project overview
|
||||
├── deploy.sh # Automated deployment script
|
||||
├── scripts/ # Executable vLLM launch scripts
|
||||
│ ├── validate-vllm.sh # Validation tool
|
||||
│ └── *.sh # Inference server scripts
|
||||
├── tests/ # Test suite
|
||||
│ └── test_validator.sh
|
||||
├── docs/ # Knowledge base
|
||||
│ ├── README.md
|
||||
│ └── *.md # Research notes
|
||||
└── failedAttempts/ # Archived scripts (for reference)
|
||||
```
|
||||
|
||||
## Running Tests
|
||||
```bash
|
||||
# Test validator on dankserver
|
||||
bash tests/test_validator.sh dankserver
|
||||
|
||||
# Test validator on dankclaw
|
||||
bash tests/test_validator.sh dankclaw
|
||||
|
||||
# Run all tests
|
||||
bash tests/test_validator.sh dankserver && bash tests/test_validator.sh dankclaw
|
||||
```
|
||||
|
||||
## Deployment
|
||||
```bash
|
||||
# Deploy all scripts to all targets
|
||||
bash deploy.sh all
|
||||
|
||||
# Deploy specific script to dankserver
|
||||
bash deploy.sh dankserver vllm-qwen36.sh
|
||||
|
||||
# Deploy specific script to dankclaw
|
||||
bash deploy.sh dankclaw vllm-thinkingcap.sh
|
||||
```
|
||||
|
||||
## Git Workflow
|
||||
|
||||
### Branching Strategy
|
||||
- `main`: Stable, working scripts only
|
||||
- `vllm-qwen36`: Active development for Qwen3.6 models
|
||||
- Feature branches: `feature/<description>` for experiments
|
||||
|
||||
### Worktree Pattern
|
||||
For parallel development:
|
||||
```bash
|
||||
# Create worktree for feature
|
||||
git worktree add ../vllm-feature feature/qwen36-awq
|
||||
|
||||
# When done, merge back
|
||||
git worktree remove ../vllm-feature
|
||||
```
|
||||
|
||||
### Commit Guidelines
|
||||
- Use descriptive commit messages: `git commit -m "Add AWQ DFlash script"`
|
||||
- Commit before deploying: `git add -A && git commit -m "Update for deployment"`
|
||||
- Push to remote: `git push origin <branch>`
|
||||
|
||||
### Deployment Flow
|
||||
1. Make changes locally
|
||||
2. Run tests: `bash tests/test_validator.sh dankserver`
|
||||
3. Commit: `git add -A && git commit -m "Description"`
|
||||
4. Deploy: `bash deploy.sh dankserver`
|
||||
5. Verify: `bash scripts/validate-vllm.sh -t dankserver`
|
||||
|
||||
## Remote Servers
|
||||
|
||||
### dankserver
|
||||
- SSH: `dank@dankserver`
|
||||
- Scripts: `~/vllm/`
|
||||
- Service: `vllm-awq-qwen36.service`
|
||||
- Model: frank-default-small (AWQ 4bit)
|
||||
- Port: 34401
|
||||
|
||||
### dankclaw
|
||||
- SSH: `dank@dankclaw`
|
||||
- Scripts: `~/vllm/`
|
||||
- Service: `vllm-thinkingcap.service`
|
||||
- Model: frank-default-large (FP8)
|
||||
- Port: 3090
|
||||
|
||||
## Troubleshooting
|
||||
- Service failed: `systemctl status <service>`
|
||||
- Container stuck: `docker stop <name> && docker rm <name>`
|
||||
- OOM error: Reduce `--max-model-len` or increase `--cpu-offload-gb`
|
||||
- Prefix caching conflict: Remove `--enable-prefix-caching` from script
|
||||
@@ -4,10 +4,27 @@ Scripts for running large language models via vLLM on two local machines.
|
||||
|
||||
## Targets
|
||||
|
||||
| Host | User | Codename | Architecture |
|
||||
|------|------|----------|-------------|
|
||||
| dankserver | dank | DankServer | NVIDIA GPU + System RAM |
|
||||
| dankclaw | dank | DankClaw | AMD Strix Halo (Shared Memory) |
|
||||
| Host | User | Codename | Architecture | Service Status |
|
||||
|------|------|----------|-------------|----------------|
|
||||
| dankserver | dank | DankServer | NVIDIA GPU + System RAM | `vllm-awq-qwen36.service` (failed) |
|
||||
| dankclaw | dank | DankClaw | AMD Strix Halo (Shared Memory) | `vllm-thinkingcap.service` (failed) |
|
||||
|
||||
## File Locations
|
||||
|
||||
### Local (vllmScripts/)
|
||||
- `scripts/` — Active inference scripts
|
||||
- `tests/` — Test suite
|
||||
- `docs/` — Knowledge base
|
||||
- `failedAttempts/` — Archived scripts
|
||||
|
||||
### Remote (dankserver)
|
||||
- `~/vllm/` — Deployed inference scripts
|
||||
- `~/vllm/failedAttempts/` — Archived scripts
|
||||
- `~/vLLM/` — Legacy project directory (vllm-qwen36.sh)
|
||||
|
||||
### Remote (dankclaw)
|
||||
- `~/vllm/` — vLLM source code (not inference scripts)
|
||||
- `~/vLLM/` — Inference scripts (if deployed)
|
||||
|
||||
## Models
|
||||
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
# deploy.sh — Deploy inference scripts to remote servers
|
||||
#
|
||||
# Usage: ./deploy.sh [TARGET] [SCRIPT]
|
||||
# TARGET: dankserver, dankclaw, or all
|
||||
# SCRIPT: Script name to deploy (default: all scripts in scripts/)
|
||||
|
||||
TARGET="${1:-all}"
|
||||
SCRIPT="${2:-}"
|
||||
|
||||
# Remote configuration
|
||||
declare -A REMOTE_HOSTS
|
||||
REMOTE_HOSTS=(
|
||||
["dankserver"]="dank@dankserver"
|
||||
["dankclaw"]="dank@dankclaw"
|
||||
)
|
||||
|
||||
declare -A REMOTE_DIRS
|
||||
REMOTE_DIRS=(
|
||||
["dankserver"]="/home/dank/vllm"
|
||||
["dankclaw"]="/home/dank/vllm"
|
||||
)
|
||||
|
||||
declare -A REMOTE_SERVICES
|
||||
REMOTE_SERVICES=(
|
||||
["dankserver"]="vllm-awq-qwen36.service"
|
||||
["dankclaw"]="vllm-thinkingcap.service"
|
||||
)
|
||||
|
||||
deploy_to() {
|
||||
local target="$1"
|
||||
local remote="${REMOTE_HOSTS[$target]}"
|
||||
local remote_dir="${REMOTE_DIRS[$target]}"
|
||||
local service="${REMOTE_SERVICES[$target]}"
|
||||
|
||||
echo "=== Deploying to $target ==="
|
||||
|
||||
# Create remote directory if it doesn't exist
|
||||
sshpass -p 'Assface.3241' ssh "$remote" "mkdir -p $remote_dir"
|
||||
|
||||
# Deploy scripts
|
||||
if [ -n "$SCRIPT" ]; then
|
||||
if [ -f "scripts/$SCRIPT" ]; then
|
||||
echo " Deploying scripts/$SCRIPT..."
|
||||
sshpass -p 'Assface.3241' scp "scripts/$SCRIPT" "$remote:$remote_dir/$SCRIPT"
|
||||
else
|
||||
echo " ERROR: scripts/$SCRIPT not found"
|
||||
return 1
|
||||
fi
|
||||
else
|
||||
for script in scripts/*.sh; do
|
||||
if [ -f "$script" ]; then
|
||||
local name=$(basename "$script")
|
||||
echo " Deploying $name..."
|
||||
sshpass -p 'Assface.3241' scp "$script" "$remote:$remote_dir/$name"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
# Make scripts executable
|
||||
if [ -n "$SCRIPT" ]; then
|
||||
sshpass -p 'Assface.3241' ssh "$remote" "chmod +x $remote_dir/$SCRIPT"
|
||||
else
|
||||
sshpass -p 'Assface.3241' ssh "$remote" "chmod +x $remote_dir/*.sh"
|
||||
fi
|
||||
|
||||
# Restart service if it exists
|
||||
echo " Restarting $service..."
|
||||
sshpass -p 'Assface.3241' ssh "$remote" "echo 'Assface.3241' | sudo -S systemctl restart $service 2>/dev/null || echo 'Service $service not found or failed'"
|
||||
|
||||
echo " Deploy to $target complete"
|
||||
echo ""
|
||||
}
|
||||
|
||||
case "$TARGET" in
|
||||
dankserver|dankclaw)
|
||||
deploy_to "$TARGET"
|
||||
;;
|
||||
all)
|
||||
for target in "${!REMOTE_HOSTS[@]}"; do
|
||||
deploy_to "$target"
|
||||
done
|
||||
;;
|
||||
*)
|
||||
echo "ERROR: Unknown target $TARGET"
|
||||
echo "Usage: $0 [dankserver|dankclaw|all] [script]"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
echo "=== Deployment complete ==="
|
||||
Reference in New Issue
Block a user