39910f2b25
Signed-off-by: Bugen Zhao <i@bugenzhao.com> Signed-off-by: Nick Hill <nickhill123@gmail.com> Signed-off-by: Eric Curtin <eric.curtin@docker.com> Signed-off-by: Dev-X25874 <283057883+Dev-X25874@users.noreply.github.com> Signed-off-by: Will.hou <1205157517@qq.com> Signed-off-by: Will.hou <willamhou@ceresman.com> Co-authored-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: Eric Curtin <eric.curtin@docker.com> Co-authored-by: Dev-X25874 <283057883+Dev-X25874@users.noreply.github.com> Co-authored-by: Will.hou <1205157517@qq.com> Co-authored-by: Will.hou <willamhou@ceresman.com> Please see https://github.com/Inferact/vllm-frontend-rs for full original commit history.
vllm-rs CLI Quick Start
Start Qwen3 with one managed vllm-rs serve command from the repo root:
HF_HUB_OFFLINE=1 \
VLLM_CPU_KVCACHE_SPACE=2 \
VLLM_HOST_IP=127.0.0.1 \
VLLM_LOOPBACK_IP=127.0.0.1 \
cargo run --bin vllm-rs -- serve \
Qwen/Qwen3-0.6B \
--python ../vllm/.venv/bin/python \
--max-model-len 512 \
-- \
--dtype float16
This launches:
- a managed headless Python
vllmengine - the Rust OpenAI-compatible frontend on
127.0.0.1:8000
All Python engine arguments must be placed after --. Arguments before -- are parsed by the Rust
frontend itself.
You can then send OpenAI-style requests to the Rust frontend:
curl http://127.0.0.1:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-0.6B",
"messages": [{"role": "user", "content": "What is the capital of France?"}],
"stream": true
}'
If you already started headless vllm yourself, use frontend instead:
cargo run --bin vllm-rs -- frontend \
--handshake-address tcp://127.0.0.1:62100 \
Qwen/Qwen3-0.6B