# Template for a new vLLM profile
# Copy: cp profiles/_template.env profiles/my-model.env
# GGUF files from lmstudio-community require stacks/llamacpp (future), not vLLM.

DATA_ROOT=/data

VLLM_MODEL=
SERVED_MODEL_NAME=my-model
QUANTIZATION=awq
VLLM_EXTRA_ARGS=--language-model-only --enforce-eager

MAX_MODEL_LEN=131072
MAX_NUM_SEQS=1
GPU_MEMORY_UTILIZATION=0.95
KV_CACHE_DTYPE=fp8

HF_TOKEN=
VLLM_PORT=8000