MODEL_CONFIG_FILE=config.json
MODEL_KEY=Qwen3.5-35B-A3B-GPTQ-Int4
MODEL_NAME=
HOST=0.0.0.0
PORT=8000
OPENAI_HOST=0.0.0.0
OPENAI_PORT=8001
TENSOR_PARALLEL_SIZE=2
GPU_MEMORY_UTILIZATION=0.92
MAX_MODEL_LEN=8192
MAX_NUM_SEQS=64
MAX_TOKENS=4096
DTYPE=bfloat16
ENFORCE_EAGER=false
TRUST_REMOTE_CODE=false
TOOL_CALL_PARSER=
ENABLE_AUTO_TOOL_CHOICE=false
REVISION=
API_KEY=