router
A high-performance and light-weight router for vLLM large scale deployment
File Explorer
Download Latest Version (.zip)- cleanup-nightly-router-builds.sh
- trigger-nightly-build.sh
- build-wheel.sh
- pipeline.yml
- README.md
- release-pipeline.yml
- config.toml
- 100-documentation.yml
- 200-bug-report.yml
- 300-feature-request.yml
- config.yml
- codeql-analysis.yml
- codespell.yml
- trivy.yaml
- PULL_REQUEST_TEMPLATE.md
- otel_disabled_path.rs
- request_processing.rs
- tokenizer_benchmark.rs
- README.md
- round_robin_config.json
- single_server_config.json
- simulate_consistent_hash.rs
- __init__.py
- launch_router.py
- mini_lb.py
- router.py
- router_args.py
- version.py
- README.md
- run_accuracy_test.sh
- run_moriio_accuracy_test.sh
- run_moriio_rdma_accuracy_test.sh
- test_lm_eval_accuracy.py
- test_pd_accuracy.py
- tp_config_sweep_test.sh
- conftest.py
- test_e2e_embeddings.py
- test_pd_router.py
- test_regular_router.py
- __init__.py
- mock_worker.py
- ports.py
- router_manager.py
- __init__.py
- test_cache_aware.py
- test_power_of_two.py
- test_random.py
- test_round_robin.py
- __init__.py
- conftest.py
- test_api_auth.py
- test_circuit_breaker.py
- test_fault_tolerance.py
- test_payload_size.py
- test_pd_routing.py
- test_rate_limiting.py
- test_retries.py
- test_service_discovery_shim.py
- test_worker_management.py
- __init__.py
- test_arg_parser.py
- test_router_config.py
- test_startup_sequence.py
- test_validation.py
- __init__.py
- conftest.py
- run_suite.py
- test_consistent_hash_policy.py
- test_launch_router.py
- build-push-vllm.sh
- decode-oom-logs.txt
- deploy-vllm.sh
- prefill-oom-logs.txt
- prefill-recipe-clean.yaml
- vllm-deepseek-deployment.yaml
- values.yaml
- benchmarking.yaml
- istio.yaml
- backend-services.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml.gotmpl
- httproute.yaml
- inferencepool.yaml
- README.md
- run-benchmark.sh
- values.yaml
- benchmarking.yaml
- istio.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml.gotmpl
- README.md
- run-benchmark.sh
- values.yaml
- vllm-service.yaml
- backend-services.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml
- README.md
- router-deployment.yaml
- router-service.yaml
- run-benchmark.sh
- values.yaml
- values.yaml
- benchmarking.yaml
- gke.yaml
- gke_tpu.yaml
- istio.yaml
- kgateway.yaml
- backend-services.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml.gotmpl
- httproute.yaml
- inferencepool.yaml
- README.md
- ROUTER_BENCHMARK_RESULTS.md
- run-benchmark.sh
- run-eval.sh
- values.yaml
- vllm-router-deployment-with-discovery.yaml
- vllm-router-deployment.yaml
- vllm-router-services.yaml
- benchmarking.yaml
- istio.yaml
- kgateway.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml.gotmpl
- README.md
- results.md
- run-benchmark.sh
- run-eval.sh
- values.yaml
- vllm-service.yaml
- backend-services.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml
- README.md
- results.md
- router-deployment.yaml
- router-service.yaml
- run-benchmark.sh
- run-eval.sh
- values.yaml
- backend-services.yaml
- cleanup.sh
- deploy.sh
- helmfile.yaml
- README.md
- results.md
- router-deployment.yaml
- router-service.yaml
- run-benchmark.sh
- run-eval.sh
- values.yaml
- values.yaml
- benchmarking.yaml
- gke.yaml
- gke_tpu.yaml
- istio.yaml
- kgateway.yaml
- BENCHMARK_RESULTS.md
- cleanup.sh
- deploy.sh
- helmfile.yaml.gotmpl
- httproute.gke.yaml
- httproute.yaml
- LOAD_BALANCING_METHODS_COMPARISON.md
- README.md
- router-deployment.yaml
- router-service.yaml
- values.yaml
- cleanup.sh
- deploy.sh
- README.md
- router-deployment.yaml
- router-pod.yaml
- router-service.yaml
- run-benchmark.sh
- test-router.sh
- start_decode.sh
- start_prefill.sh
- start_router.sh
- install.sh
- install_aws_ofi_nccl.sh
- post_benchmark_comment.py
- run_benchmarks.py
- setup-sccache.sh
- vllm_router_install.sh
- mod.rs
- types.rs
- validation.rs
- circuit_breaker.rs
- error.rs
- mod.rs
- retry.rs
- token_bucket.rs
- worker.rs
- worker_registry.rs
- mod.rs
- response_memory_store.rs
- response_noop_store.rs
- responses.rs
- cache_aware.rs
- consistent_hash.rs
- factory.rs
- hash_key.rs
- mod.rs
- power_of_two.rs
- random.rs
- registry.rs
- rendezvous_hash.rs
- round_robin.rs
- mod.rs
- spec.rs
- validation.rs
- worker_spec.rs
- dp_utils.rs
- logprobs_merge.rs
- mod.rs
- openai_router.rs
- pd_router.rs
- pd_types.rs
- router.rs
- vllm_pd_router.rs
- vllm_service_discovery.rs
- factory.rs
- header_utils.rs
- mod.rs
- router_manager.rs
- interface.rs
- mod.rs
- pool_route.rs
- prefill_decode_route.rs
- round_robin_route.rs
- routing_tree_builder.rs
- single_server_route.rs
- chat_template.rs
- factory.rs
- hub.rs
- huggingface.rs
- mock.rs
- mod.rs
- README.md
- sequence.rs
- stop.rs
- stream.rs
- tests.rs
- tiktoken.rs
- traits.rs
- json.rs
- mod.rs
- handler.rs
- lib.rs
- logger.rs
- logging.rs
- main.rs
- metrics.rs
- middleware.rs
- otel_http.rs
- otel_trace.rs
- server.rs
- service_discovery.rs
- tree.rs
- types.rs
- mock_openai_server.rs
- mock_worker.rs
- mod.rs
- test_app.rs
- api_endpoints_test.rs
- benchmark_integration.rs
- cache_aware_backward_compat_test.rs
- mock_vllm_server.py
- otel_config_test.rs
- otel_disabled_path_test.rs
- otel_integration_test.rs
- otel_openai_test.rs
- otel_trace_test.rs
- policy_registry_integration.rs
- request_formats_test.rs
- responses_api_test.rs
- streaming_tests.rs
- test_chat_template.rs
- test_chat_template_loading.rs
- test_consistent_hash_policy.rs
- test_dp_routing.rs
- test_extra_args_chat.rs
- test_openai_routing.rs
- test_pd_routing.rs
- test_prompt_input.rs
- test_transparent_proxy_routing.rs
- tokenizer_integration.rs
- .coveragerc
- .gitignore
- .pre-commit-config.yaml
- Cargo.lock
- Cargo.toml
- Dockerfile.router
- LICENSE
- Makefile
- MANIFEST.in
- pyproject.toml
- pytest.ini
- README.md
- setup.py
- test_prompt_input.json
# Installation Guide
1. Get the code
git clone https://github.com/vllm-project/router
Downloads the entire project code from GitHub to your computer.
cd router
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
Downloads and runs the official install script in one line โ this handles the full setup automatically.
pip install vllm-router
Installs the package published on PyPI directly โ no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Docker
EasyPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f Dockerfile.router -t router .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 router
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
4. Python
EasyPrerequisites
pip install vllm-router
Installs the package published on PyPI directly โ no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
5. Rust
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Rust (rustup) Installing via rustup also installs cargo.
source $HOME/.cargo/env
Type this command into your terminal and run it.
cargo --version
Type this command into your terminal and run it.
cargo build --release
Compiles the Rust project.
Set `rust-analyzer.linkedProjects` to the absolute path of `Cargo.toml`:
Type this command into your terminal and run it.
If cargo build finishes without errors, it worked. The executable is created under target/.
Pulled directly from this repo's README.
6. Make
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.
If it finishes without errors, it worked. Try running the generated executable directly.
// repository documentation
Was this content helpful?
(0 ratings)