diff --git a/docs/stable/cli/SLLM-CLI Documentation.md b/docs/stable/cli/cli_api.md similarity index 100% rename from docs/stable/cli/SLLM-CLI Documentation.md rename to docs/stable/cli/cli_api.md diff --git a/docs/stable/dev/_category_.json b/docs/stable/dev/_category_.json deleted file mode 100644 index 6050477..0000000 --- a/docs/stable/dev/_category_.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "label": "Developer Guide", - "position": 6, - "link": { - "type": "generated-index" - } -} diff --git a/docs/stable/dev/custom_backends.md b/docs/stable/dev/custom_backends.md deleted file mode 100644 index e69de29..0000000 diff --git a/docs/stable/intro.md b/docs/stable/intro.md index 31c8743..c56def2 100644 --- a/docs/stable/intro.md +++ b/docs/stable/intro.md @@ -4,7 +4,24 @@ sidebar_position: 1 # Serverless LLM + +![ServerlessLLM](../images/serverlessllm.jpg) + +ServerlessLLM is a fast, affordable, and easy-to-use library designed for multi-LLM serving, also known as [Serverless Inference](https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints.html), [Inference Endpoint](https://huggingface.co/inference-endpoints/dedicated), or [Model Endpoints](https://learn.microsoft.com/en-us/azure/machine-learning/concept-endpoints?view=azureml-api-2). This library is ideal for environments with limited GPU resources, as it allows efficient dynamic loading of models onto GPUs. By supporting high levels of GPU multiplexing, it maximizes GPU utilization without the need to dedicate GPUs to individual models. + ## Documentation ### Getting Started +- [Install ServerlessLLM](./getting_started/installation.md) +- [Deploy a ServerlessLLM cluster on your local machine](./getting_started/quickstart.md) +- [Deploy ServerlessLLM using Docker (Recommended)](./getting_started/docker_quickstart.md) +- [Deploy ServerlessLLM on a multi-machine cluster](./getting_started/multi_machine_setup.md) + +### ServerlessLLM Store + +- [Use ServerlessLLM Store in your own code](./store/quickstart.md) + +### ServerlessLLM CLI + +- [ServerlessLLM CLI Documentation](./cli/cli_api.md) diff --git a/docs/stable/serve/_category_.json b/docs/stable/serve/_category_.json deleted file mode 100644 index 9071bde..0000000 --- a/docs/stable/serve/_category_.json +++ /dev/null @@ -1,8 +0,0 @@ -{ - "label": "ServerlessLLM Serve", - "position": 3, - "link": { - "type": "generated-index", - "description": "TODO" - } -} diff --git a/docs/stable/serve/docker_deployment.md b/docs/stable/serve/docker_deployment.md deleted file mode 100644 index a100a8c..0000000 --- a/docs/stable/serve/docker_deployment.md +++ /dev/null @@ -1,2 +0,0 @@ -# Start ServerlessLLM Cluster with Docker -TODO \ No newline at end of file diff --git a/docs/stable/serve/openai_compatible_server.md b/docs/stable/serve/openai_compatible_server.md deleted file mode 100644 index d1c6e8c..0000000 --- a/docs/stable/serve/openai_compatible_server.md +++ /dev/null @@ -1,2 +0,0 @@ -# OpenAI Compatible Server -TODO \ No newline at end of file