# Data disk mount point
DATA_ROOT=/data

# --- REQUIRED before start (no default model) ---
VLLM_MODEL=
SERVED_MODEL_NAME=qwen3.6-27b

# --- Context and VRAM ---
MAX_MODEL_LEN=131072
MAX_NUM_SEQS=1
GPU_MEMORY_UTILIZATION=0.95
KV_CACHE_DTYPE=fp8

# --- Model quantization (leave empty for full-precision models) ---
QUANTIZATION=awq

# Model-specific vLLM flags (space-separated)
VLLM_EXTRA_ARGS=--language-model-only --enforce-eager --reasoning-parser qwen3

# Hugging Face token — only for gated models
HF_TOKEN=

VLLM_PORT=8000