Add validator script with target selection and test suite
This commit is contained in:
Frank
+64
-19
@@ -1,21 +1,67 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
HOST="${VLLM_HOST:-127.0.0.1}"
|
||||
PORT="${VLLM_PORT:-34401}"
|
||||
MODEL="frank-default-small"
|
||||
# Configuration
|
||||
TARGET="${VLLM_TARGET:-dankserver}"
|
||||
HOST="${VLLM_HOST:-}"
|
||||
PORT="${VLLM_PORT:-}"
|
||||
MODEL="${VLLM_MODEL:-}"
|
||||
|
||||
# Target presets
|
||||
case "$TARGET" in
|
||||
dankserver)
|
||||
HOST="${VLLM_HOST:-127.0.0.1}"
|
||||
PORT="${VLLM_PORT:-34401}"
|
||||
MODEL="${VLLM_MODEL:-frank-default-small}"
|
||||
;;
|
||||
dankclaw)
|
||||
HOST="${VLLM_HOST:-127.0.0.1}"
|
||||
PORT="${VLLM_PORT:-3090}"
|
||||
MODEL="${VLLM_MODEL:-frank-default-large}"
|
||||
;;
|
||||
*)
|
||||
echo "Unknown target: $TARGET"
|
||||
echo "Usage: $0 [-t dankserver|dankclaw] [-H host] [-P port] [-M model]"
|
||||
echo ""
|
||||
echo "Targets:"
|
||||
echo " dankserver - frank-default-small on port 34401"
|
||||
echo " dankclaw - frank-default-large on port 3090"
|
||||
echo ""
|
||||
echo "Options:"
|
||||
echo " -t TARGET Target preset (dankserver or dankclaw)"
|
||||
echo " -H HOST Override host"
|
||||
echo " -P PORT Override port"
|
||||
echo " -M MODEL Override model name"
|
||||
echo " -n N Number of streams to test (default: 4)"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
# Parse arguments
|
||||
while getopts "t:H:P:M:n:" opt; do
|
||||
case $opt in
|
||||
t) TARGET="$OPTARG" ;;
|
||||
H) HOST="$OPTARG" ;;
|
||||
P) PORT="$OPTARG" ;;
|
||||
M) MODEL="$OPTARG" ;;
|
||||
n) MAX_STREAMS="$OPTARG" ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# Default max streams if not set
|
||||
MAX_STREAMS="${MAX_STREAMS:-4}"
|
||||
|
||||
# Different prompts for each stream to avoid prefix caching effects
|
||||
PROMPT1="Explain the difference between supervised, unsupervised, and reinforcement learning in machine learning. For each type, provide a concrete real-world example, describe the training process, and discuss the advantages and limitations."
|
||||
PROMPT2="Describe the architectural differences between RISC-V and x86 instruction set architectures. Include a discussion of register files, addressing modes, and instruction encoding."
|
||||
PROMPT3="Analyze the economic impact of blockchain technology on supply chain management. Discuss the key benefits of transparency, immutability, and smart contracts."
|
||||
PROMPT4="Explain the principles of evolutionary algorithms in artificial intelligence. Describe how genetic algorithms, genetic programming, and evolutionary strategies differ in their approach to problem solving."
|
||||
PROMPTS=(
|
||||
"Explain the difference between supervised, unsupervised, and reinforcement learning in machine learning. For each type, provide a concrete real-world example, describe the training process, and discuss the advantages and limitations."
|
||||
"Describe the architectural differences between RISC-V and x86 instruction set architectures. Include a discussion of register files, addressing modes, and instruction encoding. Compare their performance for embedded systems and server workloads."
|
||||
"Analyze the economic impact of blockchain technology on supply chain management. Discuss the key benefits of transparency, immutability, and smart contracts. Compare implementation challenges of Bitcoin, Ethereum, and Hyperledger for enterprise use cases."
|
||||
"Explain the principles of evolutionary algorithms in artificial intelligence. Describe how genetic algorithms, genetic programming, and evolutionary strategies differ in their approach to problem solving. Compare their performance on optimization problems and neural network architecture search."
|
||||
)
|
||||
|
||||
PROMPTS=("$PROMPT1" "$PROMPT2" "$PROMPT3" "$PROMPT4")
|
||||
echo "=== Validating vLLM on ${HOST}:${PORT} (${TARGET}) ==="
|
||||
|
||||
echo "=== Validating vLLM on ${HOST}:${PORT} ==="
|
||||
|
||||
# Test health
|
||||
# Test health endpoint
|
||||
echo "Health check..."
|
||||
if ! curl -sf "http://${HOST}:${PORT}/health" > /dev/null 2>&1; then
|
||||
echo "FAIL: Health check failed"
|
||||
@@ -23,18 +69,17 @@ if ! curl -sf "http://${HOST}:${PORT}/health" > /dev/null 2>&1; then
|
||||
fi
|
||||
echo "OK"
|
||||
|
||||
# Test N streams sequentially (separate test for each N)
|
||||
# Each test uses different prompts to avoid caching
|
||||
for N in 1 2 3 4; do
|
||||
# Test each stream count separately
|
||||
for N in $(seq 1 "$MAX_STREAMS"); do
|
||||
echo ""
|
||||
echo "--- ${N} stream(s) ---"
|
||||
|
||||
TMPDIR=$(mktemp -d)
|
||||
START=$(date +%s%N)
|
||||
|
||||
for i in $(seq 1 $N); do
|
||||
# Use a different prompt for each stream to avoid caching
|
||||
PROMPT_IDX=$(( (i - 1) % 4 ))
|
||||
# Launch N concurrent requests with different prompts
|
||||
for i in $(seq 1 "$N"); do
|
||||
PROMPT_IDX=$(( (i - 1) % ${#PROMPTS[@]} ))
|
||||
PROMPT="${PROMPTS[$PROMPT_IDX]}"
|
||||
|
||||
curl -s -X POST "http://${HOST}:${PORT}/v1/chat/completions" \
|
||||
@@ -50,9 +95,9 @@ for N in 1 2 3 4; do
|
||||
END=$(date +%s%N)
|
||||
ELAPSED_MS=$(( (END - START) / 1000000 ))
|
||||
|
||||
# Check all responses valid
|
||||
# Validate all responses
|
||||
ALL_OK=true
|
||||
for i in $(seq 1 $N); do
|
||||
for i in $(seq 1 "$N"); do
|
||||
if ! python3 -c "import json; d=json.load(open('$TMPDIR/$i.json')); assert len(d['choices']) > 0" 2>/dev/null; then
|
||||
echo " FAIL: Response $i invalid"
|
||||
ALL_OK=false
|
||||
|
||||
Executable
+134
@@ -0,0 +1,134 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
# Test suite for validate-vllm.sh
|
||||
# Usage: bash tests/test_validator.sh [TARGET]
|
||||
|
||||
TARGET="${1:-dankserver}"
|
||||
SCRIPT="$(dirname "$0")/../scripts/validate-vllm.sh"
|
||||
PASS=0
|
||||
FAIL=0
|
||||
|
||||
pass() {
|
||||
echo "✓ PASS: $1"
|
||||
((PASS++))
|
||||
}
|
||||
|
||||
fail() {
|
||||
echo "✗ FAIL: $1"
|
||||
((FAIL++))
|
||||
}
|
||||
|
||||
# Test 1: Script exists and is executable
|
||||
if [ -x "$SCRIPT" ]; then
|
||||
pass "Script exists and is executable"
|
||||
else
|
||||
fail "Script missing or not executable"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Test 2: Script accepts -t flag
|
||||
if bash "$SCRIPT" -t dankserver --help 2>&1 | grep -q "frank-default-small"; then
|
||||
pass "Script accepts -t dankserver flag"
|
||||
else
|
||||
fail "Script does not accept -t dankserver flag"
|
||||
fi
|
||||
|
||||
# Test 3: Script accepts -H flag
|
||||
if bash "$SCRIPT" -H 127.0.0.1 --help 2>&1 | grep -q "127.0.0.1"; then
|
||||
pass "Script accepts -H host flag"
|
||||
else
|
||||
fail "Script does not accept -H host flag"
|
||||
fi
|
||||
|
||||
# Test 4: Script accepts -P flag
|
||||
if bash "$SCRIPT" -P 34401 --help 2>&1 | grep -q "34401"; then
|
||||
pass "Script accepts -P port flag"
|
||||
else
|
||||
fail "Script does not accept -P port flag"
|
||||
fi
|
||||
|
||||
# Test 5: Script accepts -M flag
|
||||
if bash "$SCRIPT" -M frank-default-small --help 2>&1 | grep -q "frank-default-small"; then
|
||||
pass "Script accepts -M model flag"
|
||||
else
|
||||
fail "Script does not accept -M model flag"
|
||||
fi
|
||||
|
||||
# Test 6: Script accepts -n flag
|
||||
if bash "$SCRIPT" -n 4 --help 2>&1 | grep -q "4"; then
|
||||
pass "Script accepts -n streams flag"
|
||||
else
|
||||
fail "Script does not accept -n streams flag"
|
||||
fi
|
||||
|
||||
# Test 7: Health check endpoint is accessible
|
||||
if curl -sf "http://${TARGET}:34401/health" > /dev/null 2>&1; then
|
||||
pass "Health check endpoint is accessible"
|
||||
else
|
||||
fail "Health check endpoint is not accessible"
|
||||
fi
|
||||
|
||||
# Test 8: Chat completions endpoint is accessible
|
||||
if curl -sf -X POST "http://${TARGET}:34401/v1/chat/completions" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "frank-default-small",
|
||||
"messages": [{"role": "user", "content": "Hello"}],
|
||||
"max_tokens": 10
|
||||
}' > /dev/null 2>&1; then
|
||||
pass "Chat completions endpoint is accessible"
|
||||
else
|
||||
fail "Chat completions endpoint is not accessible"
|
||||
fi
|
||||
|
||||
# Test 9: Response contains expected fields
|
||||
RESPONSE=$(curl -sf -X POST "http://${TARGET}:34401/v1/chat/completions" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "frank-default-small",
|
||||
"messages": [{"role": "user", "content": "Hello"}],
|
||||
"max_tokens": 10
|
||||
}')
|
||||
|
||||
if echo "$RESPONSE" | python3 -c "import json; d=json.load(sys.stdin); assert 'choices' in d" 2>/dev/null; then
|
||||
pass "Response contains 'choices' field"
|
||||
else
|
||||
fail "Response missing 'choices' field"
|
||||
fi
|
||||
|
||||
if echo "$RESPONSE" | python3 -c "import json; d=json.load(sys.stdin); assert 'usage' in d" 2>/dev/null; then
|
||||
pass "Response contains 'usage' field"
|
||||
else
|
||||
fail "Response missing 'usage' field"
|
||||
fi
|
||||
|
||||
if echo "$RESPONSE" | python3 -c "import json; d=json.load(sys.stdin); assert 'prompt_tokens' in d['usage']" 2>/dev/null; then
|
||||
pass "Response contains 'prompt_tokens' in usage"
|
||||
else
|
||||
fail "Response missing 'prompt_tokens' in usage"
|
||||
fi
|
||||
|
||||
if echo "$RESPONSE" | python3 -c "import json; d=json.load(sys.stdin); assert 'completion_tokens' in d['usage']" 2>/dev/null; then
|
||||
pass "Response contains 'completion_tokens' in usage"
|
||||
else
|
||||
fail "Response missing 'completion_tokens' in usage"
|
||||
fi
|
||||
|
||||
# Test 10: Script runs successfully (full validation)
|
||||
if bash "$SCRIPT" -t "$TARGET" -n 1 2>&1 | grep -q "Validation complete"; then
|
||||
pass "Full validation completes successfully"
|
||||
else
|
||||
fail "Full validation fails"
|
||||
fi
|
||||
|
||||
# Summary
|
||||
echo ""
|
||||
echo "=== Test Summary ==="
|
||||
echo "Passed: $PASS"
|
||||
echo "Failed: $FAIL"
|
||||
echo ""
|
||||
|
||||
if [ "$FAIL" -gt 0 ]; then
|
||||
exit 1
|
||||
fi
|
||||
Reference in New Issue
Block a user