Files
cluster-knaster/deploy/compose/gpu-vllm/.env.example
T

10 lines
182 B
Bash

SLOT_ALIAS=tier1-general
VLLM_MODEL=Qwen/Qwen3-14B-AWQ
MAX_MODEL_LEN=32768
GPU_MEM_UTIL=0.90
MAX_LORAS=4
MAX_LORA_RANK=64
MODELS_DIR=/srv/models
ADAPTERS_DIR=/srv/adapters
HF_TOKEN=