From 96f2cebbed80740b43c6755740a6146b1c5349e4 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Wed, 6 Aug 2025 18:38:50 +0100 Subject: [PATCH 1/7] Adding Kubvernor section to the implementors list Signed-off-by: Dawid Nowak --- .../manifests/gateway/kubvernor/gateway.yaml | 10 ++++++ .../gateway/kubvernor/httproute.yaml | 20 +++++++++++ site-src/guides/index.md | 36 +++++++++++++++++++ site-src/implementations/gateways.md | 11 +++++- 4 files changed, 76 insertions(+), 1 deletion(-) create mode 100644 config/manifests/gateway/kubvernor/gateway.yaml create mode 100644 config/manifests/gateway/kubvernor/httproute.yaml diff --git a/config/manifests/gateway/kubvernor/gateway.yaml b/config/manifests/gateway/kubvernor/gateway.yaml new file mode 100644 index 000000000..b37277d80 --- /dev/null +++ b/config/manifests/gateway/kubvernor/gateway.yaml @@ -0,0 +1,10 @@ +apiVersion: gateway.networking.k8s.io/v1 +kind: Gateway +metadata: + name: kubvernor-inference-gateway +spec: + gatewayClassName: kubvernor-inference-gateway + listeners: + - name: http + port: 80 + protocol: HTTP diff --git a/config/manifests/gateway/kubvernor/httproute.yaml b/config/manifests/gateway/kubvernor/httproute.yaml new file mode 100644 index 000000000..ef358f932 --- /dev/null +++ b/config/manifests/gateway/kubvernor/httproute.yaml @@ -0,0 +1,20 @@ +apiVersion: gateway.networking.k8s.io/v1 +kind: HTTPRoute +metadata: + name: llm-route +spec: + parentRefs: + - group: gateway.networking.k8s.io + kind: Gateway + name: kubvernor-inference-gateway + rules: + - backendRefs: + - group: inference.networking.x-k8s.io + kind: InferencePool + name: vllm-llama3-8b-instruct + matches: + - path: + type: PathPrefix + value: / + timeouts: + request: 300s diff --git a/site-src/guides/index.md b/site-src/guides/index.md index a1b10ed85..d7c9d30e4 100644 --- a/site-src/guides/index.md +++ b/site-src/guides/index.md @@ -244,6 +244,42 @@ This quickstart guide is intended for engineers familiar with k8s and model serv kubectl get httproute llm-route -o yaml ``` +=== "Kubvernor Rust API Gateway" + + [Kubvernor Rust API Gateway](https://github.com/kubvernor/kubvernor) is a higly experimental project so not ready for production but it supports version v0.5.1 of Inference Extension Spec. + + 1. Requirements + - Rust and Cargo installed + + 2. Run Kubvernor Rust API Gateway as documented in [README](https://github.com/kubvernor/kubvernor/blob/main/README.md) + + + 3. Deploy the Gateway + + ```bash + kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/kubvernor/gateway.yaml + ``` + + Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status: + ```bash + $ kubectl get gateway kubvernor-inference-gateway + NAME CLASS ADDRESS PROGRAMMED AGE + kubvernor-inference-gateway kubvernor-inference-gateway True 22s + ``` + + 5. Deploy the HTTPRoute + + ```bash + kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/kubvernor/httproute.yaml + ``` + + 6. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`: + + ```bash + kubectl get httproute llm-route -o yaml + ``` + + ### Try it out Wait until the gateway is ready. diff --git a/site-src/implementations/gateways.md b/site-src/implementations/gateways.md index 950c0833e..466445024 100644 --- a/site-src/implementations/gateways.md +++ b/site-src/implementations/gateways.md @@ -7,12 +7,14 @@ This project has several implementations that are planned or in progress: * [Google Kubernetes Engine][3] * [Istio][4] * [Alibaba Cloud Container Service for Kubernetes][5] +* [Kubvernor Rust API Gateway][6] [1]:#envoy-gateway [2]:#kgateway [3]:#google-kubernetes-engine [4]:#istio [5]:#alibaba-cloud-container-service-for-kubernetes +[6]:#kubernor-api-gateway ## Envoy AI Gateway @@ -85,4 +87,11 @@ by [this Issue](https://github.com/AliyunContainerService/ack-gateway-api/issues [ack]:https://www.alibabacloud.com/help/en/ack [ack-gie]:https://www.alibabacloud.com/help/en/ack/product-overview/ack-gateway-with-inference-extension -[ack-gie-usage]:https://www.alibabacloud.com/help/en/ack/ack-managed-and-ack-dedicated/user-guide/intelligent-routing-and-traffic-management-with-ack-gateway-inference-extension \ No newline at end of file +[ack-gie-usage]:https://www.alibabacloud.com/help/en/ack/ack-managed-and-ack-dedicated/user-guide/intelligent-routing-and-traffic-management-with-ack-gateway-inference-extension + +## Kubvernor Rust API Gateway +[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions v0.5.1. + +[krg]:https://github.com/kubvernor/kubvernor + + From 426f4c0d8355bdb2e67063aa5065ae480b74b74c Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Mon, 25 Aug 2025 17:22:20 +0100 Subject: [PATCH 2/7] Addressing PR comments Signed-off-by: Dawid Nowak --- config/manifests/gateway/kubvernor/gateway.yaml | 2 +- config/manifests/gateway/kubvernor/httproute.yaml | 2 +- site-src/guides/index.md | 3 ++- site-src/implementations/gateways.md | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) diff --git a/config/manifests/gateway/kubvernor/gateway.yaml b/config/manifests/gateway/kubvernor/gateway.yaml index b37277d80..89734baa7 100644 --- a/config/manifests/gateway/kubvernor/gateway.yaml +++ b/config/manifests/gateway/kubvernor/gateway.yaml @@ -1,7 +1,7 @@ apiVersion: gateway.networking.k8s.io/v1 kind: Gateway metadata: - name: kubvernor-inference-gateway + name: inference-gateway spec: gatewayClassName: kubvernor-inference-gateway listeners: diff --git a/config/manifests/gateway/kubvernor/httproute.yaml b/config/manifests/gateway/kubvernor/httproute.yaml index ef358f932..e30b56140 100644 --- a/config/manifests/gateway/kubvernor/httproute.yaml +++ b/config/manifests/gateway/kubvernor/httproute.yaml @@ -6,7 +6,7 @@ spec: parentRefs: - group: gateway.networking.k8s.io kind: Gateway - name: kubvernor-inference-gateway + name: inference-gateway rules: - backendRefs: - group: inference.networking.x-k8s.io diff --git a/site-src/guides/index.md b/site-src/guides/index.md index 5c59db55d..cd03a320b 100644 --- a/site-src/guides/index.md +++ b/site-src/guides/index.md @@ -311,7 +311,7 @@ This quickstart guide is intended for engineers familiar with k8s and model serv ```bash $ kubectl get gateway kubvernor-inference-gateway NAME CLASS ADDRESS PROGRAMMED AGE - kubvernor-inference-gateway kubvernor-inference-gateway True 22s + inference-gateway kubvernor-inference-gateway True 22s ``` 5. Deploy the HTTPRoute @@ -446,3 +446,4 @@ This quickstart guide is intended for engineers familiar with k8s and model serv ``` === "Kubvernor" + No further clean up is needed. \ No newline at end of file diff --git a/site-src/implementations/gateways.md b/site-src/implementations/gateways.md index 6f3fa4c2b..0b5e6eb2a 100644 --- a/site-src/implementations/gateways.md +++ b/site-src/implementations/gateways.md @@ -16,7 +16,7 @@ This project has several implementations that are planned or in progress: [4]:#google-kubernetes-engine [5]:#istio [6]:#kgateway -[7]:#kubernor-api-gateway +[7]:#kubvernor-rust-api-gateway ## Agentgateway From 8e66626e5c101b0c03cf5bdf86a006920fe5c2d5 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Mon, 25 Aug 2025 17:29:35 +0100 Subject: [PATCH 3/7] Addressing PR comments Signed-off-by: Dawid Nowak --- site-src/guides/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/site-src/guides/index.md b/site-src/guides/index.md index d277011a5..5d3851cd4 100644 --- a/site-src/guides/index.md +++ b/site-src/guides/index.md @@ -280,7 +280,7 @@ A cluster with: Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status: ```bash - $ kubectl get gateway kubvernor-inference-gateway + $ kubectl get gateway inference-gateway NAME CLASS ADDRESS PROGRAMMED AGE inference-gateway kubvernor-inference-gateway True 22s ``` From 061a5569c362df65afa5255ea519b6d9396f59d6 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Tue, 26 Aug 2025 09:13:02 +0100 Subject: [PATCH 4/7] Update site-src/implementations/gateways.md Co-authored-by: Nir Rozenbaum --- site-src/implementations/gateways.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/site-src/implementations/gateways.md b/site-src/implementations/gateways.md index 0b5e6eb2a..66fedd0ac 100644 --- a/site-src/implementations/gateways.md +++ b/site-src/implementations/gateways.md @@ -97,6 +97,6 @@ or within your [llm-d infrastructure](https://github.com/llm-d-incubation/llm-d- utilization for AI inference workloads. ## Kubvernor Rust API Gateway -[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions v0.5.1. +[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubvernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway is conformant with Gateway-API-Inference-Extension v0.5.1. [krg]:https://github.com/kubvernor/kubvernor \ No newline at end of file From 57194378afd1efbafa65704a613e2299b64c9943 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Wed, 3 Sep 2025 15:44:31 +0100 Subject: [PATCH 5/7] PR Review --- site-src/implementations/gateways.md | 12 ++-- site-src/implementations/gateways.md.2 | 97 ++++++++++++++++++++++++++ 2 files changed, 104 insertions(+), 5 deletions(-) create mode 100644 site-src/implementations/gateways.md.2 diff --git a/site-src/implementations/gateways.md b/site-src/implementations/gateways.md index 0b5e6eb2a..459e941fc 100644 --- a/site-src/implementations/gateways.md +++ b/site-src/implementations/gateways.md @@ -8,7 +8,7 @@ This project has several implementations that are planned or in progress: * [Google Kubernetes Engine][4] * [Istio][5] * [Kgateway][6] -* [Kubvernor Rust API Gateway][7] +* [Kubvernor][7] [1]:#agentgateway [2]:#alibaba-cloud-container-service-for-kubernetes @@ -16,7 +16,7 @@ This project has several implementations that are planned or in progress: [4]:#google-kubernetes-engine [5]:#istio [6]:#kgateway -[7]:#kubvernor-rust-api-gateway +[7]:#kubvernor ## Agentgateway @@ -96,7 +96,9 @@ gateway that can run [independently](https://gateway-api-inference-extension.sig or within your [llm-d infrastructure](https://github.com/llm-d-incubation/llm-d-infra) to improve accelerator (GPU) utilization for AI inference workloads. -## Kubvernor Rust API Gateway -[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions v0.5.1. +## Kubvernor +[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubvernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions [v0.5.1][krgc]. See the docs for the [usage][krgu]. -[krg]:https://github.com/kubvernor/kubvernor \ No newline at end of file +[krg]:https://github.com/kubvernor/kubvernor +[krgc]: https://github.com/kubernetes-sigs/gateway-api-inference-extension/tree/main/conformance/reports/v0.5.1/gateway/kubvernor +[krgu]: https://github.com/kubvernor/kubvernor/blob/main/README.md \ No newline at end of file diff --git a/site-src/implementations/gateways.md.2 b/site-src/implementations/gateways.md.2 new file mode 100644 index 000000000..466445024 --- /dev/null +++ b/site-src/implementations/gateways.md.2 @@ -0,0 +1,97 @@ +# Gateway Implementations + +This project has several implementations that are planned or in progress: + +* [Envoy AI Gateway][1] +* [Kgateway][2] +* [Google Kubernetes Engine][3] +* [Istio][4] +* [Alibaba Cloud Container Service for Kubernetes][5] +* [Kubvernor Rust API Gateway][6] + +[1]:#envoy-gateway +[2]:#kgateway +[3]:#google-kubernetes-engine +[4]:#istio +[5]:#alibaba-cloud-container-service-for-kubernetes +[6]:#kubernor-api-gateway + +## Envoy AI Gateway + +[Envoy AI Gateway][aigw-home] is an open source project built on top of +[Envoy][envoy-org] and [Envoy Gateway][envoy-gateway] to handle request traffic +from application clients to GenAI services. The features and capabilities are outlined [here][aigw-capabilities]. Use the [quickstart][aigw-quickstart] to get Envoy AI Gateway running with Gateway API in a few simple steps. + +Progress towards supporting this project is tracked with a [GitHub +Issue](https://github.com/envoyproxy/ai-gateway/issues/423). + +[aigw-home]:https://aigateway.envoyproxy.io/ +[envoy-org]:https://github.com/envoyproxy +[envoy-gateway]: https://gateway.envoyproxy.io/ +[aigw-capabilities]:https://aigateway.envoyproxy.io/docs/capabilities/ +[aigw-quickstart]:https://aigateway.envoyproxy.io/docs/capabilities/gateway-api-inference-extension + +## Kgateway + +[Kgateway](https://kgateway.dev/) is a feature-rich, Kubernetes-native +ingress controller and next-generation API gateway. Kgateway brings the +full power and community support of Gateway API to its existing control-plane +implementation. + +Progress towards supporting this project is tracked with a [GitHub +Issue](https://github.com/kgateway-dev/kgateway/issues/10411). + +## Google Kubernetes Engine + +[Google Kubernetes Engine (GKE)][gke] is a managed Kubernetes platform offered +by Google Cloud. GKE's implementation of the Gateway API is through the [GKE +Gateway controller][gke-gateway] which provisions Google Cloud Load Balancers +for Pods in GKE clusters. + +The GKE Gateway controller supports weighted traffic splitting, mirroring, +advanced routing, multi-cluster load balancing and more. See the docs to deploy +[private or public Gateways][gke-gateway-deploy] and also [multi-cluster +Gateways][gke-multi-cluster-gateway]. + +Progress towards supporting this project is tracked with a [GitHub +Issue](https://github.com/GoogleCloudPlatform/gke-gateway-api/issues/20). + +[gke]:https://cloud.google.com/kubernetes-engine +[gke-gateway]:https://cloud.google.com/kubernetes-engine/docs/concepts/gateway-api +[gke-gateway-deploy]:https://cloud.google.com/kubernetes-engine/docs/how-to/deploying-gateways +[gke-multi-cluster-gateway]:https://cloud.google.com/kubernetes-engine/docs/how-to/deploying-multi-cluster-gateways + +## Istio + +[Istio](https://istio.io/) is an open source service mesh and gateway implementation. +It provides a fully compliant implementation of the Kubernetes Gateway API for cluster ingress traffic control. +For service mesh users, Istio also fully supports east-west (including [GAMMA](https://gateway-api.sigs.k8s.io/mesh/)) traffic management within the mesh. + +Gateway API Inference Extension support is being tracked by this [GitHub +Issue](https://github.com/istio/istio/issues/55768). + +## Alibaba Cloud Container Service for Kubernetes + +[Alibaba Cloud Container Service for Kubernetes (ACK)][ack] is a managed Kubernetes platform +offered by Alibaba Cloud. The implementation of the Gateway API in ACK is through the +[ACK Gateway with Inference Extension][ack-gie] component, which introduces model-aware, +GPU-efficient load balancing for AI workloads beyond basic HTTP routing. + +The ACK Gateway with Inference Extension implements the Gateway API Inference Extension +and provides optimized routing for serving generative AI workloads, +including weighted traffic splitting, mirroring, advanced routing, etc. +See the docs for the [usage][ack-gie-usage]. + +Progress towards supporting Gateway API Inference Extension is being tracked +by [this Issue](https://github.com/AliyunContainerService/ack-gateway-api/issues/1). + +[ack]:https://www.alibabacloud.com/help/en/ack +[ack-gie]:https://www.alibabacloud.com/help/en/ack/product-overview/ack-gateway-with-inference-extension +[ack-gie-usage]:https://www.alibabacloud.com/help/en/ack/ack-managed-and-ack-dedicated/user-guide/intelligent-routing-and-traffic-management-with-ack-gateway-inference-extension + +## Kubvernor Rust API Gateway +[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions v0.5.1. + +[krg]:https://github.com/kubvernor/kubvernor + + From 4e2ac44304dc09d8825234a5996ff9f1fb1869f9 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Wed, 3 Sep 2025 16:15:01 +0100 Subject: [PATCH 6/7] PR Review Signed-off-by: Dawid Nowak --- site-src/guides/index.md | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/site-src/guides/index.md b/site-src/guides/index.md index 5d3851cd4..1b3c3560d 100644 --- a/site-src/guides/index.md +++ b/site-src/guides/index.md @@ -262,17 +262,15 @@ A cluster with: kubectl get httproute llm-route -o yaml ``` -=== "Kubvernor Rust API Gateway" +=== "Kubvernor" [Kubvernor Rust API Gateway](https://github.com/kubvernor/kubvernor) is a higly experimental project so not ready for production but it supports version v0.5.1 of Inference Extension Spec. + - 1. Requirements - - Rust and Cargo installed - - 2. Run Kubvernor Rust API Gateway as documented in [README](https://github.com/kubvernor/kubvernor/blob/main/README.md) + 1. Compile and run Kubvernor Rust API Gateway as documented in [README](https://github.com/kubvernor/kubvernor/blob/main/README.md) - 3. Deploy the Gateway + 2. Deploy the Gateway ```bash kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/kubvernor/gateway.yaml @@ -285,13 +283,13 @@ A cluster with: inference-gateway kubvernor-inference-gateway True 22s ``` - 5. Deploy the HTTPRoute + 3. Deploy the HTTPRoute ```bash kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/kubvernor/httproute.yaml ``` - 6. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`: + 4. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`: ```bash kubectl get httproute llm-route -o yaml From 284781861e9fe60566b3e3ac24918c58d44b1154 Mon Sep 17 00:00:00 2001 From: Dawid Nowak Date: Thu, 4 Sep 2025 21:07:56 +0100 Subject: [PATCH 7/7] Removing extra file Signed-off-by: Dawid Nowak --- site-src/implementations/gateways.md.2 | 97 -------------------------- 1 file changed, 97 deletions(-) delete mode 100644 site-src/implementations/gateways.md.2 diff --git a/site-src/implementations/gateways.md.2 b/site-src/implementations/gateways.md.2 deleted file mode 100644 index 466445024..000000000 --- a/site-src/implementations/gateways.md.2 +++ /dev/null @@ -1,97 +0,0 @@ -# Gateway Implementations - -This project has several implementations that are planned or in progress: - -* [Envoy AI Gateway][1] -* [Kgateway][2] -* [Google Kubernetes Engine][3] -* [Istio][4] -* [Alibaba Cloud Container Service for Kubernetes][5] -* [Kubvernor Rust API Gateway][6] - -[1]:#envoy-gateway -[2]:#kgateway -[3]:#google-kubernetes-engine -[4]:#istio -[5]:#alibaba-cloud-container-service-for-kubernetes -[6]:#kubernor-api-gateway - -## Envoy AI Gateway - -[Envoy AI Gateway][aigw-home] is an open source project built on top of -[Envoy][envoy-org] and [Envoy Gateway][envoy-gateway] to handle request traffic -from application clients to GenAI services. The features and capabilities are outlined [here][aigw-capabilities]. Use the [quickstart][aigw-quickstart] to get Envoy AI Gateway running with Gateway API in a few simple steps. - -Progress towards supporting this project is tracked with a [GitHub -Issue](https://github.com/envoyproxy/ai-gateway/issues/423). - -[aigw-home]:https://aigateway.envoyproxy.io/ -[envoy-org]:https://github.com/envoyproxy -[envoy-gateway]: https://gateway.envoyproxy.io/ -[aigw-capabilities]:https://aigateway.envoyproxy.io/docs/capabilities/ -[aigw-quickstart]:https://aigateway.envoyproxy.io/docs/capabilities/gateway-api-inference-extension - -## Kgateway - -[Kgateway](https://kgateway.dev/) is a feature-rich, Kubernetes-native -ingress controller and next-generation API gateway. Kgateway brings the -full power and community support of Gateway API to its existing control-plane -implementation. - -Progress towards supporting this project is tracked with a [GitHub -Issue](https://github.com/kgateway-dev/kgateway/issues/10411). - -## Google Kubernetes Engine - -[Google Kubernetes Engine (GKE)][gke] is a managed Kubernetes platform offered -by Google Cloud. GKE's implementation of the Gateway API is through the [GKE -Gateway controller][gke-gateway] which provisions Google Cloud Load Balancers -for Pods in GKE clusters. - -The GKE Gateway controller supports weighted traffic splitting, mirroring, -advanced routing, multi-cluster load balancing and more. See the docs to deploy -[private or public Gateways][gke-gateway-deploy] and also [multi-cluster -Gateways][gke-multi-cluster-gateway]. - -Progress towards supporting this project is tracked with a [GitHub -Issue](https://github.com/GoogleCloudPlatform/gke-gateway-api/issues/20). - -[gke]:https://cloud.google.com/kubernetes-engine -[gke-gateway]:https://cloud.google.com/kubernetes-engine/docs/concepts/gateway-api -[gke-gateway-deploy]:https://cloud.google.com/kubernetes-engine/docs/how-to/deploying-gateways -[gke-multi-cluster-gateway]:https://cloud.google.com/kubernetes-engine/docs/how-to/deploying-multi-cluster-gateways - -## Istio - -[Istio](https://istio.io/) is an open source service mesh and gateway implementation. -It provides a fully compliant implementation of the Kubernetes Gateway API for cluster ingress traffic control. -For service mesh users, Istio also fully supports east-west (including [GAMMA](https://gateway-api.sigs.k8s.io/mesh/)) traffic management within the mesh. - -Gateway API Inference Extension support is being tracked by this [GitHub -Issue](https://github.com/istio/istio/issues/55768). - -## Alibaba Cloud Container Service for Kubernetes - -[Alibaba Cloud Container Service for Kubernetes (ACK)][ack] is a managed Kubernetes platform -offered by Alibaba Cloud. The implementation of the Gateway API in ACK is through the -[ACK Gateway with Inference Extension][ack-gie] component, which introduces model-aware, -GPU-efficient load balancing for AI workloads beyond basic HTTP routing. - -The ACK Gateway with Inference Extension implements the Gateway API Inference Extension -and provides optimized routing for serving generative AI workloads, -including weighted traffic splitting, mirroring, advanced routing, etc. -See the docs for the [usage][ack-gie-usage]. - -Progress towards supporting Gateway API Inference Extension is being tracked -by [this Issue](https://github.com/AliyunContainerService/ack-gateway-api/issues/1). - -[ack]:https://www.alibabacloud.com/help/en/ack -[ack-gie]:https://www.alibabacloud.com/help/en/ack/product-overview/ack-gateway-with-inference-extension -[ack-gie-usage]:https://www.alibabacloud.com/help/en/ack/ack-managed-and-ack-dedicated/user-guide/intelligent-routing-and-traffic-management-with-ack-gateway-inference-extension - -## Kubvernor Rust API Gateway -[Kubvernor Rust API Gateway][krg] is an open-source, highly experimental implementation of API controller in Rust programming language. Currently, Kubernor supports Envoy Proxy. The project aims to be as generic as possible so Kubvernor can be used to manage/deploy different gateways (Envoy, Nginx, HAProxy, etc.). Kubvernor Rust API Gateway implements Inference Extensions v0.5.1. - -[krg]:https://github.com/kubvernor/kubvernor - -