Merge branch 'main' into update-inference-providers-docs-automated-pr

Author: Wauplin

docs/inference-providers/_toctree.yml

@@ -23,6 +23,8 @@
     title: Featherless AI
   - local: providers/fireworks-ai
     title: Fireworks
+  - local: providers/groq
+    title: Groq
   - local: providers/hyperbolic
     title: Hyperbolic
   - local: providers/hf-inference

docs/inference-providers/index.md

@@ -20,6 +20,7 @@ Here is the complete list of partners integrated with Inference Providers, and t
 | [Fal AI](./providers/fal-ai)             |                       |                       |                    |       ✅       |       ✅       |
 | [Featherless AI](./providers/featherless-ai) |    ✅           |                        |                     |             |                |
 | [Fireworks](./providers/fireworks-ai)    |           ✅           |           ✅           |                    |               |               |
+| [Groq](./providers/groq)                  |           ✅           |                       |                    |               |               |
 | [HF Inference](./providers/hf-inference) |           ✅           |           ✅           |         ✅          |       ✅       |               |
 | [Hyperbolic](./providers/hyperbolic)     |           ✅           |           ✅           |                    |               |               |
 | [Nebius](./providers/nebius)             |           ✅           |           ✅           |         ✅         |       ✅       |               |

docs/inference-providers/providers/groq.md

@@ -0,0 +1,69 @@
+<!---
+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 groq's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/groq.handlebars`.
+
+### Logos
+
+If you want to update groq'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 `groq-light.png` and `groq-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.
+--->
+
+# Groq
+
+<div class="flex justify-center">
+    <a href="https://groq.com/" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/groq-light.png"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/groq-dark.png"/>
+    </a>
+</div>
+
+<div class="flex">
+    <a href="https://huggingface.co/groq" 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>
+
+Groq is fast AI inference. Their groundbreaking LPU technology delivers record-setting performance and efficiency for GenAI models. With custom chips specifically designed for AI inference workloads and a deterministic, software-first approach, Groq eliminates the bottlenecks of conventional hardware to enable real-time AI applications with predictable latency and exceptional throughput so developers can build fast.
+
+For latest pricing, visit our [pricing page](https://groq.com/pricing/).
+
+## Resources
+ - **Website**: https://groq.com/
+ - **Documentation**: https://console.groq.com/docs
+ - **Community Forum**: https://community.groq.com/
+ - **X**: [@GroqInc](https://x.com/GroqInc)
+ - **LinkedIn**: [Groq](https://www.linkedin.com/company/groq/)
+ - **YouTube**: [Groq](https://www.youtube.com/@GroqInc)
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=text-generation
+    providersMapping={ {"groq":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen/qwen3-32b"} } }
+conversational />
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=image-text-to-text
+    providersMapping={ {"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"} } }
+conversational />
+

docs/inference-providers/tasks/chat-completion.md

@@ -25,6 +25,7 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/inference-p
 - [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B): Smaller variant of one of the most powerful models.
 - [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): Very powerful text generation model trained to follow instructions.
 - [microsoft/phi-4](https://huggingface.co/microsoft/phi-4): Powerful text generation model by Microsoft.
+- [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M): Strong conversational model that supports very long instructions.
 - [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct): Text generation model used to write code.
 - [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1): Powerful reasoning based open large language model.
 

docs/inference-providers/tasks/text-generation.md

@@ -30,6 +30,7 @@ For more details about the `text-generation` task, check out its [dedicated page
 - [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B): Smaller variant of one of the most powerful models.
 - [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): Very powerful text generation model trained to follow instructions.
 - [microsoft/phi-4](https://huggingface.co/microsoft/phi-4): Powerful text generation model by Microsoft.
+- [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M): Strong conversational model that supports very long instructions.
 - [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct): Text generation model used to write code.
 - [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1): Powerful reasoning based open large language model.