# vllm server configuration
# Used by: nix run .#vllm-start-llm  and  nix run .#vllm-start-embed

# Force CPU backend — no CUDA/ROCm GPU on this machine
VLLM_TARGET_DEVICE=cpu

VLLM_LLM_MODEL=Qwen/Qwen3-0.6B
VLLM_LLM_PORT=8000
# VLLM_LLM_EXTRA_ARGS=--dtype bfloat16 --max-model-len 4096

VLLM_EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
VLLM_EMBED_PORT=8001
# VLLM_EMBED_EXTRA_ARGS=--dtype bfloat16