Cargo.lock
Cargo.toml
MANIFEST.in
README.md
pyproject.toml
setup.py
py_src/vllm_router/__init__.py
py_src/vllm_router/launch_router.py
py_src/vllm_router/mini_lb.py
py_src/vllm_router/router.py
py_src/vllm_router/router_args.py
py_src/vllm_router/version.py
py_src/vllm_router.egg-info/PKG-INFO
py_src/vllm_router.egg-info/SOURCES.txt
py_src/vllm_router.egg-info/dependency_links.txt
py_src/vllm_router.egg-info/entry_points.txt
py_src/vllm_router.egg-info/not-zip-safe
py_src/vllm_router.egg-info/requires.txt
py_src/vllm_router.egg-info/top_level.txt
src/handler.rs
src/kv_hash.rs
src/lib.rs
src/logger.rs
src/logging.rs
src/main.rs
src/metrics.rs
src/middleware.rs
src/otel_http.rs
src/otel_trace.rs
src/server.rs
src/service_discovery.rs
src/token_estimator.rs
src/tree.rs
src/types.rs
src/wasm_middleware.rs
src/backend/control.rs
src/backend/convert.rs
src/backend/detect.rs
src/backend/frontend.rs
src/backend/grpc.rs
src/backend/health.rs
src/backend/mod.rs
src/backend/openai.rs
src/backend/preprocess.rs
src/backend/vllm_frontend.rs
src/config/mod.rs
src/config/types.rs
src/config/validation.rs
src/core/circuit_breaker.rs
src/core/error.rs
src/core/mod.rs
src/core/retry.rs
src/core/token_bucket.rs
src/core/worker.rs
src/core/worker_registry.rs
src/data_connector/mod.rs
src/data_connector/response_memory_store.rs
src/data_connector/response_noop_store.rs
src/data_connector/responses.rs
src/kv_index/discovery.rs
src/kv_index/indexer.rs
src/kv_index/mod.rs
src/kv_index/subscriber.rs
src/kv_index/types.rs
src/kv_index/wire.rs
src/policies/cache_aware.rs
src/policies/consistent_hash.rs
src/policies/factory.rs
src/policies/hash_key.rs
src/policies/mod.rs
src/policies/power_of_two.rs
src/policies/random.rs
src/policies/registry.rs
src/policies/rendezvous_hash.rs
src/policies/round_robin.rs
src/program_scheduling/contracts.rs
src/program_scheduling/diagnostics.rs
src/program_scheduling/domain.rs
src/program_scheduling/factors.rs
src/program_scheduling/identity.rs
src/program_scheduling/lineage.rs
src/program_scheduling/mod.rs
src/program_scheduling/observations.rs
src/program_scheduling/policy.rs
src/program_scheduling/request_pool.rs
src/program_scheduling/runtime.rs
src/program_scheduling/scheduler.rs
src/program_scheduling/scheduler_admission.rs
src/program_scheduling/scheduler_fairness.rs
src/program_scheduling/scheduler_global.rs
src/program_scheduling/scheduler_lifecycle.rs
src/program_scheduling/scheduler_state.rs
src/program_scheduling/binding/mod.rs
src/protocols/mod.rs
src/protocols/spec.rs
src/protocols/validation.rs
src/protocols/worker_spec.rs
src/routers/factory.rs
src/routers/header_utils.rs
src/routers/mod.rs
src/routers/router_manager.rs
src/routers/http/dp_utils.rs
src/routers/http/logprobs_merge.rs
src/routers/http/mod.rs
src/routers/http/openai_router.rs
src/routers/http/pd_router.rs
src/routers/http/pd_types.rs
src/routers/http/program_adapter.rs
src/routers/http/router.rs
src/routers/http/vllm_pd_router.rs
src/routers/http/vllm_service_discovery.rs
src/routes/interface.rs
src/routes/mod.rs
src/routes/pool_route.rs
src/routes/prefill_decode_route.rs
src/routes/round_robin_route.rs
src/routes/routing_tree_builder.rs
src/routes/single_server_route.rs
src/tokenizer/cache.rs
src/tokenizer/chat_template.rs
src/tokenizer/factory.rs
src/tokenizer/hub.rs
src/tokenizer/huggingface.rs
src/tokenizer/mock.rs
src/tokenizer/mod.rs
src/tokenizer/sequence.rs
src/tokenizer/stop.rs
src/tokenizer/stream.rs
src/tokenizer/tests.rs
src/tokenizer/tiktoken.rs
src/tokenizer/traits.rs
src/utils/json.rs
src/utils/mod.rs
tests/test_bench_prefix_kvhit.py
wit/router-middleware.wit