21 lines
641 B
Bash
21 lines
641 B
Bash
# Copy to .env on the deployment host and adjust values there.
|
|
# Do not commit real tokens, private paths, or credentials.
|
|
|
|
VLLM_CONTAINER_NAME=llm-vllm-text
|
|
VLLM_IMAGE=vllm/vllm-openai:latest
|
|
VLLM_MODEL_ID=Qwen/Qwen3-4B-Instruct-2507
|
|
VLLM_SERVED_MODEL_NAME=qwen3-4b-instruct
|
|
VLLM_LORA_MODULES=qwen3-4b-1c=/models/adapters/1c/qwen3-4b-1c-lora-v1
|
|
VLLM_MAX_LORAS=1
|
|
VLLM_HOST_PORT=8000
|
|
VLLM_GPU_MEMORY_UTILIZATION=0.90
|
|
VLLM_MAX_MODEL_LEN=32768
|
|
VLLM_DTYPE=auto
|
|
|
|
# Local model/cache paths on docker-gpu.cin.su.
|
|
HOST_MODELS_DIR=/models
|
|
HOST_HF_CACHE_DIR=/models/cache/huggingface
|
|
|
|
# Set on the host only if the model source requires it.
|
|
HF_TOKEN=
|