Changes: - CLAUDE.md: Update OOM fix validation status - Add comprehensive documentation (30+ markdown reports) - LSTM encoder varmap bug fix (tft/lstm_encoder.rs:290) - Quantized LSTM layer matching fix (tft/quantized_lstm.rs) - Hyperopt paths module (ml/src/hyperopt/paths.rs) - Training path tests for all adapters (DQN, MAMBA-2, PPO, TFT) - Checkpoint integrity tests - Script cleanup: Remove 29 obsolete deployment scripts - Archive old scripts to scripts/archive/ - New deployment utilities: check_gpu_availability.py, monitor_hyperopt.sh Validation: - OOM fixes validated: 5/5 trials successful (pod b6kc3mc5lbjiro) - Batch-size-max 256 tested successfully - All hyperopt adapters working correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
217 lines
6.8 KiB
Bash
Executable File
217 lines
6.8 KiB
Bash
Executable File
#!/bin/bash
|
|
# =============================================================================
|
|
# FOXHUNT RUNPOD DEPLOYMENT TEST SCRIPT
|
|
# =============================================================================
|
|
# Tests the deployment script without actually deploying
|
|
# Validates prerequisites and dry-run checks without uploads
|
|
#
|
|
# Usage:
|
|
# ./scripts/runpod_deploy_test.sh
|
|
# =============================================================================
|
|
|
|
set -e
|
|
|
|
# Color codes
|
|
RED='\033[0;31m'
|
|
GREEN='\033[0;32m'
|
|
YELLOW='\033[1;33m'
|
|
BLUE='\033[0;34m'
|
|
CYAN='\033[0;36m'
|
|
NC='\033[0m'
|
|
|
|
success() {
|
|
echo -e "${GREEN}✓${NC} $1"
|
|
}
|
|
|
|
error() {
|
|
echo -e "${RED}✗${NC} $1"
|
|
}
|
|
|
|
warning() {
|
|
echo -e "${YELLOW}⚠${NC} $1"
|
|
}
|
|
|
|
section() {
|
|
echo ""
|
|
echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
|
|
echo -e "${BLUE}$1${NC}"
|
|
echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
|
|
}
|
|
|
|
section "Runpod Deployment Test - Dry Run"
|
|
|
|
ISSUES_FOUND=0
|
|
|
|
# Test 1: Cargo
|
|
echo -e "\n${CYAN}Test 1: Cargo${NC}"
|
|
if command -v cargo &> /dev/null; then
|
|
RUST_VERSION=$(cargo --version | awk '{print $2}')
|
|
success "Cargo installed: $RUST_VERSION"
|
|
else
|
|
error "Cargo not found"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 2: Docker
|
|
echo -e "\n${CYAN}Test 2: Docker${NC}"
|
|
if command -v docker &> /dev/null; then
|
|
if docker info &> /dev/null 2>&1; then
|
|
DOCKER_VERSION=$(docker --version | awk '{print $3}' | tr -d ',')
|
|
success "Docker running: $DOCKER_VERSION"
|
|
else
|
|
error "Docker daemon not running"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
else
|
|
error "Docker not found"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 3: AWS CLI
|
|
echo -e "\n${CYAN}Test 3: AWS CLI${NC}"
|
|
if command -v aws &> /dev/null; then
|
|
AWS_VERSION=$(aws --version 2>&1 | awk '{print $1}' | cut -d'/' -f2)
|
|
success "AWS CLI installed: $AWS_VERSION"
|
|
else
|
|
error "AWS CLI not found"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 4: Environment variables
|
|
echo -e "\n${CYAN}Test 4: Environment Variables${NC}"
|
|
|
|
if [ -n "${RUNPOD_S3_ENDPOINT:-}" ]; then
|
|
success "RUNPOD_S3_ENDPOINT: $RUNPOD_S3_ENDPOINT"
|
|
else
|
|
error "RUNPOD_S3_ENDPOINT not set"
|
|
warning "Set with: export RUNPOD_S3_ENDPOINT=https://s3api-us-ca-1.runpod.io"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
if [ "${AWS_PROFILE:-}" = "runpod" ]; then
|
|
success "AWS_PROFILE: runpod"
|
|
else
|
|
error "AWS_PROFILE not set to 'runpod'"
|
|
warning "Set with: export AWS_PROFILE=runpod"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
if [ -n "${DOCKER_USERNAME:-}" ]; then
|
|
success "DOCKER_USERNAME: $DOCKER_USERNAME"
|
|
else
|
|
error "DOCKER_USERNAME not set"
|
|
warning "Set with: export DOCKER_USERNAME=jgrusewski"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 5: AWS Profile
|
|
echo -e "\n${CYAN}Test 5: AWS Profile Configuration${NC}"
|
|
if [ "${AWS_PROFILE:-}" = "runpod" ]; then
|
|
if aws configure list --profile runpod &> /dev/null; then
|
|
success "AWS profile 'runpod' configured"
|
|
|
|
# Show credentials (redacted)
|
|
ACCESS_KEY=$(aws configure get aws_access_key_id --profile runpod)
|
|
if [ -n "$ACCESS_KEY" ]; then
|
|
REDACTED_KEY="${ACCESS_KEY:0:8}***"
|
|
success "Access Key: $REDACTED_KEY"
|
|
fi
|
|
else
|
|
error "AWS profile 'runpod' not configured"
|
|
warning "Configure with: aws configure --profile runpod"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
fi
|
|
|
|
# Test 6: Test data
|
|
echo -e "\n${CYAN}Test 6: Test Data Files${NC}"
|
|
TEST_DATA_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/test_data"
|
|
|
|
if [ -d "$TEST_DATA_DIR" ]; then
|
|
PARQUET_COUNT=$(ls -1 "$TEST_DATA_DIR"/*.parquet 2>/dev/null | wc -l)
|
|
if [ "$PARQUET_COUNT" -gt 0 ]; then
|
|
success "Found $PARQUET_COUNT parquet files in $TEST_DATA_DIR"
|
|
|
|
# Show first 3 files
|
|
for file in $(ls "$TEST_DATA_DIR"/*.parquet 2>/dev/null | head -3); do
|
|
filename=$(basename "$file")
|
|
SIZE=$(stat -c%s "$file" 2>/dev/null || stat -f%z "$file")
|
|
SIZE_MB=$(awk "BEGIN {printf \"%.2f\", $SIZE/1024/1024}")
|
|
echo " - $filename ($SIZE_MB MB)"
|
|
done
|
|
else
|
|
error "No parquet files found in $TEST_DATA_DIR"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
else
|
|
error "Test data directory not found: $TEST_DATA_DIR"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 7: Dockerfile
|
|
echo -e "\n${CYAN}Test 7: Dockerfile${NC}"
|
|
DOCKERFILE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/Dockerfile.runpod"
|
|
|
|
if [ -f "$DOCKERFILE" ]; then
|
|
success "Dockerfile.runpod exists"
|
|
else
|
|
error "Dockerfile.runpod not found"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 8: Entrypoint script
|
|
echo -e "\n${CYAN}Test 8: Entrypoint Script${NC}"
|
|
ENTRYPOINT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/entrypoint.sh"
|
|
|
|
if [ -f "$ENTRYPOINT" ]; then
|
|
if [ -x "$ENTRYPOINT" ]; then
|
|
success "entrypoint.sh exists and is executable"
|
|
else
|
|
warning "entrypoint.sh exists but not executable"
|
|
echo " Fix with: chmod +x $ENTRYPOINT"
|
|
fi
|
|
else
|
|
error "entrypoint.sh not found"
|
|
ISSUES_FOUND=$((ISSUES_FOUND + 1))
|
|
fi
|
|
|
|
# Test 9: S3 connectivity
|
|
echo -e "\n${CYAN}Test 9: S3 Connectivity (Optional)${NC}"
|
|
if [ -n "${RUNPOD_S3_ENDPOINT:-}" ] && [ "${AWS_PROFILE:-}" = "runpod" ]; then
|
|
echo "Testing S3 connectivity to $RUNPOD_S3_ENDPOINT..."
|
|
|
|
# Try to list buckets (may fail if no permissions, but tests connectivity)
|
|
if aws s3 ls --endpoint-url "$RUNPOD_S3_ENDPOINT" --profile runpod &> /dev/null; then
|
|
success "S3 connectivity works"
|
|
else
|
|
warning "S3 connectivity test failed (may need to create bucket first)"
|
|
echo " This is OK if you haven't created a Network Volume yet"
|
|
fi
|
|
else
|
|
warning "Skipping S3 connectivity test (missing env vars)"
|
|
fi
|
|
|
|
# Summary
|
|
section "Test Summary"
|
|
|
|
if [ $ISSUES_FOUND -eq 0 ]; then
|
|
echo -e "${GREEN}✅ All tests passed! Ready for deployment.${NC}"
|
|
echo ""
|
|
echo "Run deployment with:"
|
|
echo " ./scripts/runpod_deploy.sh"
|
|
else
|
|
echo -e "${RED}❌ Found $ISSUES_FOUND issue(s). Fix before deploying.${NC}"
|
|
echo ""
|
|
echo "Quick fixes:"
|
|
echo " 1. Install missing tools (cargo, docker, aws cli)"
|
|
echo " 2. Set environment variables:"
|
|
echo " export RUNPOD_S3_ENDPOINT=https://s3api-us-ca-1.runpod.io"
|
|
echo " export AWS_PROFILE=runpod"
|
|
echo " export DOCKER_USERNAME=jgrusewski"
|
|
echo " 3. Configure AWS profile:"
|
|
echo " aws configure --profile runpod"
|
|
echo " 4. Re-run this test script"
|
|
fi
|
|
|
|
exit $ISSUES_FOUND
|