You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
# config.yaml for vLLM configuration
|
|
|
|
model: Qwen/Qwen3-4B
|
|
host: "127.0.0.1"
|
|
port: 6379
|
|
uvicorn-log-level: "info"
|
|
gpu-memory-utilization: 0.75
|
|
max-model-len: 4096
|
|
# quantization: awq
|
|
# run with
|
|
# vllm serve --config config.yaml
|