27 lines
871 B
Bash
27 lines
871 B
Bash
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
ROOT=/home/daniel/aeon-spark-test/h3
|
|
MODEL_DIR="$ROOT/models/Qwen3.8-27B-NVFP4"
|
|
COMPOSE_FILE="$ROOT/qwen38-vllm/compose.qwen38-vllm.yml"
|
|
|
|
if [[ ! -f "$MODEL_DIR/model.safetensors" ]]; then
|
|
echo "model.safetensors is not present yet: $MODEL_DIR/model.safetensors" >&2
|
|
echo "Wait for qwen38-27b-nvfp4-download to finish before starting vLLM." >&2
|
|
exit 1
|
|
fi
|
|
|
|
python3 - <<'PY'
|
|
import json
|
|
from pathlib import Path
|
|
|
|
tokenizer = Path('/home/daniel/aeon-spark-test/h3/models/Qwen3.8-27B-NVFP4/tokenizer.json')
|
|
truncation = json.loads(tokenizer.read_text(encoding='utf-8')).get('truncation')
|
|
if truncation is not None:
|
|
raise SystemExit(f'tokenizer truncation must be null, got: {truncation!r}')
|
|
print('tokenizer truncation: null')
|
|
PY
|
|
|
|
mkdir -p "$ROOT/vllm-cache"
|
|
docker compose -f "$COMPOSE_FILE" up -d
|
|
docker logs -f qwen38-vllm
|