From 7149361275cab53fdc9d4f184a10d9dceba2e0f0 Mon Sep 17 00:00:00 2001 From: Dominik Safaric Date: Mon, 8 Dec 2025 23:59:28 +0100 Subject: [PATCH 1/8] Add the SageMaker docs --- docs.json | 7 ++++ integrations/sagemaker.mdx | 71 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+) create mode 100644 integrations/sagemaker.mdx diff --git a/docs.json b/docs.json index 3d259b5..f4e4fb0 100644 --- a/docs.json +++ b/docs.json @@ -103,6 +103,13 @@ "extensions/rf-pfn" ] }, + { + "group": "Integrations", + "icon": "cloud", + "pages": [ + "integrations/sagemaker" + ] + }, { "group": "Use Cases", "pages": [ diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx new file mode 100644 index 0000000..a610672 --- /dev/null +++ b/integrations/sagemaker.mdx @@ -0,0 +1,71 @@ +--- +title: "Amazon SageMaker" +description: "Guide to setting up TabPFN-2.5 on Amazon SageMaker." +--- + +Deploy TabPFN-2.5 directly in your AWS environment in just a few steps. + +By subscribing to TabPFN-2.5 through the AWS SageMaker Marketplace, you can automatically provision and configure TabPFN-2.5 inside your own AWS account - ensuring your data and inference remain within your private AWS networks. + + +Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. All usage is subject to the [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). + + +TabPFN-2.5 on SageMaker is ideal for teams already operating on AWS who want to benefit from TabPFN-2.5’s performance without managing infrastructure themselves, while maintaining strong data security within their AWS environment: + +- Complete data privacy - Runs in your AWS account; data never leaves your infrastructure. +- Minimal infrastructure work - AWS handles GPU provisioning and deployment. +- AWS native - Seamless integration with your existing environment and security policies. + +### Getting Started + +Setting up TabPFN-2.5 in your AWS account is easy and takes just a few steps. + +1. Open the SageMaker Marketplace listing. +2. Click “View Purchase Options.” +3. Scroll to the bottom of the page and select “Subscribe.” + +After subscribing, Amazon SageMaker may take several minutes to confirm your agreement. This delay is normal, even for free-of-charge products. + +Next, set up an **Endpoint** in the AWS Management Console and SageMaker AI. +1. Navigate to SageMaker AI. +2. Select the AWS region where you want to deploy TabPFN-2.5. +3. In the left-hand panel, open "AWS Marketplace resources", go to the "AWS Marketplace subscriptions" tab, and select TabPFN-2.5. +4. Click "Actions" on the right-hand side and choose "Create endpoint". + +You will now be prompted to set a Model name and assign an IAM execution role for the model. You can use the creation wizard to streamline this step. +After clicking Next, you will be asked to either select an existing endpoint configuration or create a new one. TabPFN-2.5 requires at least one NVIDIA T4 or P4 GPU instance, and for larger datasets we recommend using more capable hardware such as **ml.g5.2xlarge** or **ml.p4.4xlarge** for improved performance. +Take a moment to confirm that your chosen instance type meets your workload needs before proceeding. + +The full list of supported machine types for real-time inference and batch transform can be found in the Marketplace listing details page. + +Once you have clicked on Submit, AWS will automatically set up TabPFN-2.5 in your AWS account and you're good to go! + + + + Step-by-step instructions for running inference with TabPFN-2.5 on SageMaker. + + + + A guided notebook demonstrating how to use TabPFN-2.5 for inference on SageMaker. + + + +### Limitations + +#### Payload size +SageMaker Models on the AWS Marketplace do not allow any outbound network calls - including calls to AWS-managed services such as S3. As a result, all data must be included directly in the inference request payload, and AWS enforces a 25 MB maximum payload size. + +TabPFN-2.5 supports two input formats for inference: +- `application/json` - a JSON-encoded request body. +- `multipart/form-data` - containing the datasets Parquet files. + +Both formats must remain within the 25 MB SageMaker payload limit. Because Parquet is compressed, the `multipart/form-data` option generally allows you to send more rows or features within the same size constraint. \ No newline at end of file From a08c197097125ed6594efb82b0bccf4c2d954653 Mon Sep 17 00:00:00 2001 From: Dominik Safaric Date: Tue, 9 Dec 2025 11:55:10 +0100 Subject: [PATCH 2/8] Add the Loom recording --- integrations/sagemaker.mdx | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx index a610672..b1ef791 100644 --- a/integrations/sagemaker.mdx +++ b/integrations/sagemaker.mdx @@ -19,6 +19,14 @@ TabPFN-2.5 on SageMaker is ideal for teams already operating on AWS who want to ### Getting Started + + Setting up TabPFN-2.5 in your AWS account is easy and takes just a few steps. 1. Open the SageMaker Marketplace listing. From 896c51b10266bce235d1cec4add1ef7b767896bd Mon Sep 17 00:00:00 2001 From: Dominik Safaric Date: Tue, 9 Dec 2025 14:22:44 +0100 Subject: [PATCH 3/8] Change wording for SageMaker --- integrations/sagemaker.mdx | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx index b1ef791..821c5cc 100644 --- a/integrations/sagemaker.mdx +++ b/integrations/sagemaker.mdx @@ -15,7 +15,7 @@ TabPFN-2.5 on SageMaker is ideal for teams already operating on AWS who want to - Complete data privacy - Runs in your AWS account; data never leaves your infrastructure. - Minimal infrastructure work - AWS handles GPU provisioning and deployment. -- AWS native - Seamless integration with your existing environment and security policies. +- AWS native - Seamless integration with your existing environment and security policies. ### Getting Started @@ -43,7 +43,7 @@ Next, set up an **Endpoint** in the AWS Management Console and SageMaker AI. You will now be prompted to set a Model name and assign an IAM execution role for the model. You can use the creation wizard to streamline this step. After clicking Next, you will be asked to either select an existing endpoint configuration or create a new one. TabPFN-2.5 requires at least one NVIDIA T4 or P4 GPU instance, and for larger datasets we recommend using more capable hardware such as **ml.g5.2xlarge** or **ml.p4.4xlarge** for improved performance. -Take a moment to confirm that your chosen instance type meets your workload needs before proceeding. +Take a moment to confirm that your chosen instance type meets your workload needs before proceeding. The full list of supported machine types for real-time inference and batch transform can be found in the Marketplace listing details page. @@ -74,6 +74,6 @@ SageMaker Models on the AWS Marketplace do not allow any outbound network calls TabPFN-2.5 supports two input formats for inference: - `application/json` - a JSON-encoded request body. -- `multipart/form-data` - containing the datasets Parquet files. +- `multipart/form-data` - containing the dataset as Parquet files. Both formats must remain within the 25 MB SageMaker payload limit. Because Parquet is compressed, the `multipart/form-data` option generally allows you to send more rows or features within the same size constraint. \ No newline at end of file From 3cbcebaae6b92a03014d63c045da9bbd66d9a829 Mon Sep 17 00:00:00 2001 From: Dominik Safaric <153173064+safaricd@users.noreply.github.com> Date: Tue, 16 Dec 2025 12:43:22 +0100 Subject: [PATCH 4/8] Update integrations/sagemaker.mdx Co-authored-by: Noah Hollmann --- integrations/sagemaker.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx index 821c5cc..52ef250 100644 --- a/integrations/sagemaker.mdx +++ b/integrations/sagemaker.mdx @@ -5,7 +5,7 @@ description: "Guide to setting up TabPFN-2.5 on Amazon SageMaker." Deploy TabPFN-2.5 directly in your AWS environment in just a few steps. -By subscribing to TabPFN-2.5 through the AWS SageMaker Marketplace, you can automatically provision and configure TabPFN-2.5 inside your own AWS account - ensuring your data and inference remain within your private AWS networks. +By subscribing to TabPFN-2.5 through the AWS SageMaker Marketplace, you can automatically provision and configure TabPFN-2.5 inside your own AWS account - ensuring your data remains within your private AWS networks. Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. All usage is subject to the [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). From 265ec461580bf460a416ccd104654a9897e68edb Mon Sep 17 00:00:00 2001 From: Dominik Safaric <153173064+safaricd@users.noreply.github.com> Date: Tue, 16 Dec 2025 12:44:26 +0100 Subject: [PATCH 5/8] Update integrations/sagemaker.mdx Co-authored-by: Noah Hollmann --- integrations/sagemaker.mdx | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx index 52ef250..a7c20fc 100644 --- a/integrations/sagemaker.mdx +++ b/integrations/sagemaker.mdx @@ -8,7 +8,9 @@ Deploy TabPFN-2.5 directly in your AWS environment in just a few steps. By subscribing to TabPFN-2.5 through the AWS SageMaker Marketplace, you can automatically provision and configure TabPFN-2.5 inside your own AWS account - ensuring your data remains within your private AWS networks. -Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. All usage is subject to the [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). +Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. Model weights released under [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). This license is designed to be permissive for research and internal evaluation. +It *explicitly allows* testing, evaluation, and internal benchmarking, so an organization can download the model and run preliminary assessments on its own datasets. The key restriction is that the model, its derivatives, and its outputs cannot be used for any commercial or production purpose. This includes, but is not limited to, revenue-generating products, competitive benchmarking for procurement, client deliverables, or using the model’s results for internal commercial decision-making. +For all production use cases, we offer a *Commercial Enterprise License*. This provides access to our proprietary high-speed inference engine, dedicated support, integration tooling, and other internal models. Please contact us at sales@priorlabs.ai for commercial licensing inquiries. TabPFN-2.5 on SageMaker is ideal for teams already operating on AWS who want to benefit from TabPFN-2.5’s performance without managing infrastructure themselves, while maintaining strong data security within their AWS environment: From 1df33424af4d30cdc3534e7913a3bd5e8584b26a Mon Sep 17 00:00:00 2001 From: Dominik Safaric Date: Tue, 16 Dec 2025 12:47:41 +0100 Subject: [PATCH 6/8] Fix formatting issue with --- integrations/sagemaker.mdx | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/integrations/sagemaker.mdx b/integrations/sagemaker.mdx index a7c20fc..092e1a5 100644 --- a/integrations/sagemaker.mdx +++ b/integrations/sagemaker.mdx @@ -3,22 +3,22 @@ title: "Amazon SageMaker" description: "Guide to setting up TabPFN-2.5 on Amazon SageMaker." --- -Deploy TabPFN-2.5 directly in your AWS environment in just a few steps. - By subscribing to TabPFN-2.5 through the AWS SageMaker Marketplace, you can automatically provision and configure TabPFN-2.5 inside your own AWS account - ensuring your data remains within your private AWS networks. - -Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. Model weights released under [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). This license is designed to be permissive for research and internal evaluation. -It *explicitly allows* testing, evaluation, and internal benchmarking, so an organization can download the model and run preliminary assessments on its own datasets. The key restriction is that the model, its derivatives, and its outputs cannot be used for any commercial or production purpose. This includes, but is not limited to, revenue-generating products, competitive benchmarking for procurement, client deliverables, or using the model’s results for internal commercial decision-making. -For all production use cases, we offer a *Commercial Enterprise License*. This provides access to our proprietary high-speed inference engine, dedicated support, integration tooling, and other internal models. Please contact us at sales@priorlabs.ai for commercial licensing inquiries. - - TabPFN-2.5 on SageMaker is ideal for teams already operating on AWS who want to benefit from TabPFN-2.5’s performance without managing infrastructure themselves, while maintaining strong data security within their AWS environment: - Complete data privacy - Runs in your AWS account; data never leaves your infrastructure. - Minimal infrastructure work - AWS handles GPU provisioning and deployment. - AWS native - Seamless integration with your existing environment and security policies. + +Using TabPFN-2.5 on the AWS SageMaker Marketplace is free of charge; you only pay for the underlying AWS compute. Model weights released under [TabPFN-2.5 License](https://huggingface.co/Prior-Labs/tabpfn_2_5/blob/main/LICENSE). This license is designed to be permissive for research and internal evaluation. + +It *explicitly allows* testing, evaluation, and internal benchmarking, so an organization can download the model and run preliminary assessments on its own datasets. The key restriction is that the model, its derivatives, and its outputs cannot be used for any commercial or production purpose. This includes, but is not limited to, revenue-generating products, competitive benchmarking for procurement, client deliverables, or using the model’s results for internal commercial decision-making. + +For all production use cases, we offer a *Commercial Enterprise License*. This provides access to our proprietary high-speed inference engine, dedicated support, integration tooling, and other internal models. Please contact us at sales@priorlabs.ai for commercial licensing inquiries. + + ### Getting Started