Add NVIDIA inference provider documentation

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

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)           |                       |                       |                    |      ✅       |      ✅       |       ✅       |

docs/inference-providers/providers/nvidia.md

@@ -0,0 +1,50 @@
+<!---
+WARNING
+
+This markdown file has been generated from a script. Please do not edit it directly.
+
+### Template
+
+If you want to update the content related to nvidia's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/nvidia.handlebars`.
+
+### Logos
+
+If you want to update nvidia's logo, upload a file by opening a PR on https://huggingface.co/datasets/huggingface/documentation-images/tree/main/inference-providers/logos. Ping @wauplin and @celinah on the PR to let them know you uploaded a new logo.
+Logos must be in .png format and be named `nvidia-light.png` and `nvidia-dark.png`. Visit https://huggingface.co/settings/theme to switch between light and dark mode and check that the logos are displayed correctly.
+
+### Generation script
+
+For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
+--->
+
+# NVIDIA
+
+> [!TIP]
+> All supported NVIDIA models can be found [here](https://huggingface.co/models?inference_provider=nvidia&sort=trending)
+
+<div class="flex justify-center">
+    <a href="https://www.nvidia.com/" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/nvidia-light.png"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/nvidia-dark.png"/>
+    </a>
+</div>
+
+<div class="flex">
+    <a href="https://huggingface.co/nvidia" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg.svg"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg-dark.svg"/>
+    </a>
+</div>
+
+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
+
+

scripts/inference-providers/scripts/generate.ts

@@ -46,6 +46,7 @@ const PROVIDERS_URLS: Record<string, string> = {
   //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/",

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}}}