Files

12 lines
364 B
Bash

# Copy to .env on the Spark; use absolute paths. Do not commit .env.
HF_CACHE_DIR=/path/to/huggingface
API_KEY_FILE=/path/to/qwen.key
API_PORT=8000
BIND_ADDRESS=0.0.0.0
MODEL_HTTP_PROXY=
MODEL_HTTPS_PROXY=
GPU_MEMORY_UTILIZATION=0.80
MAX_NUM_SEQS=4
# Optional offline build: local tag that resolves to the pinned base digest.
# BASE_IMAGE=local/vllm-base:0bfc7a15