diff --git a/docs/inference-providers/_toctree.yml b/docs/inference-providers/_toctree.yml index c288e25f20..abcfd26f23 100644 --- a/docs/inference-providers/_toctree.yml +++ b/docs/inference-providers/_toctree.yml @@ -120,6 +120,8 @@ title: Novita - local: providers/nscale title: Nscale + - local: providers/nvidia + title: NVIDIA - local: providers/ovhcloud title: OVHcloud AI Endpoints - local: providers/publicai diff --git a/docs/inference-providers/index.md b/docs/inference-providers/index.md index 8feac7d0c3..911f0d932c 100644 --- a/docs/inference-providers/index.md +++ b/docs/inference-providers/index.md @@ -23,6 +23,7 @@ Our platform integrates with leading AI infrastructure providers, giving you acc | [Hyperbolic](./providers/hyperbolic) | ✅ | ✅ | | | | | | [Novita](./providers/novita) | ✅ | ✅ | | | ✅ | | | [Nscale](./providers/nscale) | ✅ | ✅ | | ✅ | | | +| [NVIDIA](./providers/nvidia) | ✅ | | | | | | | [OVHcloud AI Endpoints](./providers/ovhcloud)| ✅ | ✅ | | | | | | [Public AI](./providers/publicai) | ✅ | | | | | | | [Replicate](./providers/replicate) | | | | ✅ | ✅ | ✅ | diff --git a/docs/inference-providers/providers/nvidia.md b/docs/inference-providers/providers/nvidia.md new file mode 100644 index 0000000000..9112797e08 --- /dev/null +++ b/docs/inference-providers/providers/nvidia.md @@ -0,0 +1,50 @@ + + +# NVIDIA + +> [!TIP] +> All supported NVIDIA models can be found [here](https://huggingface.co/models?inference_provider=nvidia&sort=trending) + +
+ + + + +
+ +
+ + + + +
+ +NVIDIA provides high-performance AI inference infrastructure through NVIDIA NIM microservices and accelerated computing platforms, with access to production-ready models for enterprise and developer workloads. + +For details on pricing, usage policies, and data handling, please refer to NVIDIA's official API documentation and terms. + +## Resources +- **Website**: https://www.nvidia.com/ +- **API Catalog**: https://build.nvidia.com/ +- **Documentation**: https://docs.api.nvidia.com/ + +## Supported tasks + + diff --git a/scripts/inference-providers/scripts/generate.ts b/scripts/inference-providers/scripts/generate.ts index 21607f41f4..e98c250a00 100644 --- a/scripts/inference-providers/scripts/generate.ts +++ b/scripts/inference-providers/scripts/generate.ts @@ -46,6 +46,7 @@ const PROVIDERS_URLS: Record = { //nebius: "https://nebius.com/", novita: "https://novita.ai/", nscale: "https://www.nscale.com/", + nvidia: "https://www.nvidia.com/", ovhcloud: "https://www.ovhcloud.com/", publicai: "https://publicai.co/", replicate: "https://replicate.com/", diff --git a/scripts/inference-providers/templates/providers/nvidia.handlebars b/scripts/inference-providers/templates/providers/nvidia.handlebars new file mode 100644 index 0000000000..2c24efabe0 --- /dev/null +++ b/scripts/inference-providers/templates/providers/nvidia.handlebars @@ -0,0 +1,19 @@ +# NVIDIA + +> [!TIP] +> All supported NVIDIA models can be found [here](https://huggingface.co/models?inference_provider=nvidia&sort=trending) + +{{{logoSection}}} + +{{{followUsSection}}} + +NVIDIA provides high-performance AI inference infrastructure through NVIDIA NIM microservices and accelerated computing platforms, with access to production-ready models for enterprise and developer workloads. + +For details on pricing, usage policies, and data handling, please refer to NVIDIA's official API documentation and terms. + +## Resources +- **Website**: https://www.nvidia.com/ +- **API Catalog**: https://build.nvidia.com/ +- **Documentation**: https://docs.api.nvidia.com/ + +{{{tasksSection}}}