semantic-router

Release v0.3.0

Container Images (GHCR)

Always pin to a version tag in production — it is immutable.

docker pull ghcr.io/vllm-project/semantic-router/extproc:v0.3.0
docker pull ghcr.io/vllm-project/semantic-router/vllm-sr:v0.3.0
docker pull ghcr.io/vllm-project/semantic-router/anthropic-shim:v0.3.0
docker pull ghcr.io/vllm-project/semantic-router/dashboard:v0.3.0
docker pull ghcr.io/vllm-project/semantic-router/operator:v0.3.0
docker pull ghcr.io/vllm-project/semantic-router/operator-bundle:v0.3.0

Helm Chart

# Install a specific version
helm install semantic-router \
  oci://ghcr.io/vllm-project/charts/semantic-router \
  --version 0.3.0 \
  --namespace vllm-semantic-router-system --create-namespace

# Upgrade to this version
helm upgrade semantic-router \
  oci://ghcr.io/vllm-project/charts/semantic-router \
  --version 0.3.0 \
  --namespace vllm-semantic-router-system

Python Package (PyPI)

pip install vllm-sr==0.3.0

Rust Crate (crates.io)

[dependencies]
candle-semantic-router = "0.3.0"

vllm-sr-sim ships on its own vllm-sr-sim-v* tag and is currently at 0.1.0.

See the upgrade and rollback runbook for step-by-step upgrade and rollback instructions.

What's Changed

• security: sanitize error responses to prevent infrastructure leakage by @yossiovadia in https://github.com/vllm-project/semantic-router/pull/1451
• [Dashboard]Polish dashboard auth and setup flow by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1494
• [Doc] Update paper: Add author, Kubernetes note by @srampal in https://github.com/vllm-project/semantic-router/pull/1493
• [Doc] tolerate README admonition list style by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1495
• [Dashboard]: Fix OpenClaw room chat history management by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1503
• fix(dashboard): stop setup wizard validation loop by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1504
• project: add roadmap for v0.3 by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1527
• Fix traditional Candle BERT classifier registration after initialization by @pugafran in https://github.com/vllm-project/semantic-router/pull/1496
• test(memory): align e2e tests with direct per-turn storage flow by @yehuditkerido in https://github.com/vllm-project/semantic-router/pull/1433
• [Misc] Fix memory E2E tests with black by @drivebyer in https://github.com/vllm-project/semantic-router/pull/1543
• [CLI][CI/Build] Support isolated local stacks and harness routing by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1542
• website: refine homepage system-brain narrative by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1545
• [Bugfix][Router] Wrong /v1-suffixed OpenAI base URLs for vector store search by @drivebyer in https://github.com/vllm-project/semantic-router/pull/1541
• feat(classification): add entropy-based multi-category domain matching and signal confidence scores by @noalimoy in https://github.com/vllm-project/semantic-router/pull/1497
• observability: add Prometheus metric and tracing for cache write skips by @mkoushni in https://github.com/vllm-project/semantic-router/pull/1529
• feat(domain-signal): add UseModernBERT factory branch for category classifier by @noalimoy in https://github

Installation

curl -fsSL https://vllm-semantic-router.com/install.sh | bash

What's Changed

See the full changelog below.

What's Changed

• [Bugfix] Fix getRecommendedModel to return real model names from config by @henschwartz in https://github.com/vllm-project/semantic-router/pull/933
• [CI] test(response-api): add E2E translation tests for Response API by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/881
• [Doc] Fix installation typo by @shernshiou in https://github.com/vllm-project/semantic-router/pull/965
• [CI] ci(e2e): add Response API K8s integration test workflow by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/882
• fix: initialize batched embedding modelfor qwen3 semantic cache by @liavweiss in https://github.com/vllm-project/semantic-router/pull/954
• fix(dashboard): resolve config update permission denied error by @henschwartz in https://github.com/vllm-project/semantic-router/pull/962
• docs: fix index dsiplay error by @yuluo-yx in https://github.com/vllm-project/semantic-router/pull/959
• [CI/Build][Dashboard] Fix OpenShift config map paths and dashboard build by @nerdalert in https://github.com/vllm-project/semantic-router/pull/951
• test(dashboard): add file persistence tests for config updates by @henschwartz in https://github.com/vllm-project/semantic-router/pull/963
• [Doc] website versions multilingual for release v0.1 by @samzong in https://github.com/vllm-project/semantic-router/pull/925
• feat(vllm-sr): add dashboard support to Python CLI by @yehuditkerido in https://github.com/vllm-project/semantic-router/pull/960
• fix(dashboard): return 404 instead of 500 when tools_db.json not found by @henschwartz in https://github.com/vllm-project/semantic-router/pull/972
• [Bugfix] Fix PII mapping path to match deployed model directory by @nerdalert in https://github.com/vllm-project/semantic-router/pull/970
• feat: re-enable EmbeddingGemma-300m support by @liavweiss in https://github.com/vllm-project/semantic-router/pull/816
• feat [llm-katan] Support running llm-katan on XPU Platform by @chaojun-zhang in https://github.com/vllm-project/semantic-router/pull/969
• [Misc] 🔧 chore(pre-commit): show file count instead of list by @samzong in https://github.com/vllm-project/semantic-router/pull/968
• [Misc] 🔧 chore(make): add deps.mk for func-e and unified external binary tool management by @samzong in https://github.com/vllm-project/semantic-router/pull/886
• Fix(CI): Resolve The E2E Testing by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1013
• feat(dashboard): add Python CLI config format support by @yehuditkerido in https://github.com/vllm-project/semantic-router/pull/1019
• feat(cli): add Podman container runtime support by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/982
• [Misc]: remove legacy Kustomize manifests in favor of Helm chart by @abdallahsamabd in https://github.com/vllm-project/semantic-router/pull/978
• [Feat] implement Signal Parallelism in EvaluateAllSignals by @GOavi101 in https://github.com/vllm-project/semantic-router/pull/1023
• [Feat][CI/Build] Add OpenShift simulator backend for vSR by @nerdalert in https://github.com/vllm-project/semantic-router/pull/981
• [Feat] Add multi-model routing demo by @anushapant in https://github.com/vllm-project/semantic-router/pull/1025
• [Feat]: Enable CLI-based Helm deployment with smart defaults by @abdallahsamabd in https://github.com/vllm-project/semantic-router/pull/957
• Optimize: Speed-Up Signal Extraction by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1027
• fix: set file descriptor limits to 65536 to resolve Envoy initialization failure by @liavweiss in https://github.com/vllm-project/semantic-router/pull/1026
• [Bugfix] Fix keyword matching i

Release Blog: https://blog.vllm.ai/2026/01/05/vllm-sr-iris.html

What's Changed

• feat: support auto-enable reasoning mode based on intention by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/1
• fix: remove no needed todo and verify CI by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/2
• project: add bench and site owners by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/4
• project: add code of conduct by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/5
• chore: unify docker images by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/6
• fix: use the correct go test file name. by @yafengio in https://github.com/vllm-project/semantic-router/pull/7
• ci: disable notify action for now by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/10
• docs: semantic cache stale types and implementation by @gluonfield in https://github.com/vllm-project/semantic-router/pull/9
• chore: rm readthedocs as its deprecated by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/12
• Removed redundant / from code img by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/13
• chore: Update CONTRIBUTING.md by @cryo-zd in https://github.com/vllm-project/semantic-router/pull/17
• chore: add DCO requirement in CONTRIBUTING.md by @cryo-zd in https://github.com/vllm-project/semantic-router/pull/18
• fix(cache): cleanup expired cache entries during update operations by @QIN2DIM in https://github.com/vllm-project/semantic-router/pull/16
• chore(logging): unify the logging method by @ZeroZ-lab in https://github.com/vllm-project/semantic-router/pull/19
• fix:make reasoning effort configurable by @OneZero-Y in https://github.com/vllm-project/semantic-router/pull/21
• docs: add vsr star history diagram by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/26
• docs: add repo link in CONTRIBUTING.md by @cryo-zd in https://github.com/vllm-project/semantic-router/pull/27
• project: add acknowledgements to huggingface-candle by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/28
• chore: replace fmt.Printf with log.Printf for logging by @cryo-zd in https://github.com/vllm-project/semantic-router/pull/29
• doc: update workflow to create config.yaml by @rootfs in https://github.com/vllm-project/semantic-router/pull/30
• feat: implement batch classification API by @OneZero-Y in https://github.com/vllm-project/semantic-router/pull/24
• chore: 1) install rust if not present 2) expose bench params in env var by @rootfs in https://github.com/vllm-project/semantic-router/pull/54
• feat: Add comprehensive monitoring metrics for batch classification API by @OneZero-Y in https://github.com/vllm-project/semantic-router/pull/58
• docs: add pre-commit requirement code quality checks to contributing by @OneZero-Y in https://github.com/vllm-project/semantic-router/pull/60
• feat: reasoning model controller by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/56
• test: add unit tests for getModelFamilyAndTemplateParam by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/63
• docs: add reasoning model metrics by @tao12345666333 in https://github.com/vllm-project/semantic-router/pull/64
• feat: add test framework for classifier with dependency injection by @aeft in https://github.com/vllm-project/semantic-router/pull/57
• project: add vllm semantic router v0.1 roadmap by @Xunzhuo in https://github.com/vllm-project/semantic-router/pull/22
• test: add unit test around ttft pkg by @yuluo-yx in https://github.com/vllm-project/semantic-router/pull/68
• feat: code polish on classifier by @yuluo-yx in https://github.com/vllm-project/semantic-router/pull/67
• feat: robust model name filter for DeepSeek by @tao12