Pricing

Documentation

Blog

Case Studies

Get Access

Batch LLM Inference is better with Sutro

Run LLM Batch Jobs in Hours, Not Days, at a Fraction of the Cost.

Get Started

Generate a question/answer pair for the following chunk of vLLM documentation

Inputs

Outputs

Intro to vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Loading Models

vLM models can be loaded in two different ways. To pass a loaded model into the vLLM framework for further processing and inference without reloading it from disk or a model hub, first start by generating


Using the Open AI Server

Run:ai Model Streamer is a library to read tensors in concurrency, while streaming it to GPU memory. Further reading can be found in Run:ai Model Streamer Documentation.

vLLM supports loading weights in Safetensors format using the Run:ai Model Streamer. You first need to install vLLM RunAI optional dependency:

Question: Is vLLM compatible with all open-source models? ...

Question: How do I load a custom model from HuggingFace? ...

Question: Can I use the OpenAI compatible server to replace calls...

+128 more…

Batch LLM Inference is better with Sutro

Run LLM Batch Jobs in Hours, Not Days, at a Fraction of the Cost.

Get Started

Generate a question/answer pair for the following chunk of vLLM documentation

Inputs

Outputs

Intro to vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Loading Models

vLM models can be loaded in two different ways. To pass a loaded model into the vLLM framework for further processing and inference without reloading it from disk or a model hub, first start by generating


Using the Open AI Server

Run:ai Model Streamer is a library to read tensors in concurrency, while streaming it to GPU memory. Further reading can be found in Run:ai Model Streamer Documentation.

vLLM supports loading weights in Safetensors format using the Run:ai Model Streamer. You first need to install vLLM RunAI optional dependency:

Question: Is vLLM compatible with all open-source models? ...

Question: How do I load a custom model from HuggingFace? ...

Question: Can I use the OpenAI compatible server to replace calls...

+128 more…

Entity extraction

Extract structured data from millions of documents at a fraction of the cost

Transform massive amounts of free-form text into analytics-ready datasets. Run LLM batch jobs to turn unstructured data into structured insights without the pain of managing your own infrastructure.

Get Access

Generate a question/answer pair for the following chunk of vLLM documentation

Inputs

Outputs

Intro to vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Loading Models

vLM models can be loaded in two different ways. To pass a loaded model into the vLLM framework for further processing and inference without reloading it from disk or a model hub, first start by generating


Using the Open AI Server

Run:ai Model Streamer is a library to read tensors in concurrency, while streaming it to GPU memory. Further reading can be found in Run:ai Model Streamer Documentation.

vLLM supports loading weights in Safetensors format using the Run:ai Model Streamer. You first need to install vLLM RunAI optional dependency:

Question: Is vLLM compatible with all open-source models? ...

Question: How do I load a custom model from HuggingFace? ...

Question: Can I use the OpenAI compatible server to replace calls...

+128 more…

Batch LLM Inference is better with Sutro

Run LLM Batch Jobs in Hours, Not Days, at a Fraction of the Cost.

Get Started

Generate a question/answer pair for the following chunk of vLLM documentation

Inputs

Outputs

Intro to vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Loading Models

vLM models can be loaded in two different ways. To pass a loaded model into the vLLM framework for further processing and inference without reloading it from disk or a model hub, first start by generating


Using the Open AI Server

Run:ai Model Streamer is a library to read tensors in concurrency, while streaming it to GPU memory. Further reading can be found in Run:ai Model Streamer Documentation.

vLLM supports loading weights in Safetensors format using the Run:ai Model Streamer. You first need to install vLLM RunAI optional dependency:

Question: Is vLLM compatible with all open-source models? ...

Question: How do I load a custom model from HuggingFace? ...

Question: Can I use the OpenAI compatible server to replace calls...

+128 more…

Batch LLM Inference is better with Sutro

Run LLM Batch Jobs in Hours, Not Days, at a Fraction of the Cost.

Get Started

Generate a question/answer pair for the following chunk of vLLM documentation

Inputs

Outputs

Intro to vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Loading Models

vLM models can be loaded in two different ways. To pass a loaded model into the vLLM framework for further processing and inference without reloading it from disk or a model hub, first start by generating


Using the Open AI Server

Run:ai Model Streamer is a library to read tensors in concurrency, while streaming it to GPU memory. Further reading can be found in Run:ai Model Streamer Documentation.

vLLM supports loading weights in Safetensors format using the Run:ai Model Streamer. You first need to install vLLM RunAI optional dependency:

Question: Is vLLM compatible with all open-source models? ...

Question: How do I load a custom model from HuggingFace? ...

Question: Can I use the OpenAI compatible server to replace calls...

+128 more…

Purpose-Built for Scalable Extraction

Ship faster results without complex infrastructure. Sutro's Python SDK is purpose-built to scale up any LLM workflow for entity extraction.

import sutro as so

from pydantic import BaseModel

class ReviewClassifier(BaseModel):

sentiment: str

user_reviews = '.

User_reviews.csv

User_reviews-1.csv

User_reviews-2.csv

User_reviews-3.csv

system_prompt = 'Classify the review as positive, neutral, or negative.'

results = so.infer(user_reviews, system_prompt, output_schema=ReviewClassifier)

Progress: 1% | 1/514,879 | Input tokens processed: 0.41m, Tokens generated: 591k

█░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░

Prototype

Start small and iterate fast on your LLM batch workflows. Accelerate experiments by testing your extraction schema on Sutro before committing to large jobs.

Scale

Scale your LLM workflows so your team can do more in less time. Process billions of tokens in hours, not days, with no infrastructure headaches or exploding costs.

Integrate

Seamlessly connect Sutro to your existing LLM workflows. Sutro's Python SDK is compatible with popular data orchestration tools, like Airflow and Dagster.

Scale Effortlessly

Confidently handle millions of requests and billions of tokens at a time. Extract data from entire web crawls or document archives without the pain of managing infrastructure.

Reduce Costs by 10x or More

Reduce Costs by 10x or More

Reduce Costs by 10x or More

Get results faster and reduce costs by parallelizing your LLM calls through Sutro. Process massive extraction jobs in hours, not days.

From Idea to Insights, Simplified

Shorten development cycles by getting feedback from large batch jobs in as little as minutes before scaling up to process your full dataset.

Structured Extraction

Longer description goes here, should span multiple lines.

Invoice data extraction

Automate pulling key information from financial documents and invoices at scale.

Website data extraction

Crawl millions of web pages and extract analytics-ready datasets for your company or your customers.

Document summarization

Condense large volumes of text into concise summaries for faster analysis.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights.

RAG data preparation

Easily convert large corpuses of free-form text into vector representations for semantic search.

Structured Extraction

Longer description goes here, should span multiple lines.

Invoice data extraction

Automate pulling key information from financial documents and invoices at scale.

Website data extraction

Crawl millions of web pages and extract analytics-ready datasets for your company or your customers.

Document summarization

Condense large volumes of text into concise summaries for faster analysis.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights.

RAG data preparation

Easily convert large corpuses of free-form text into vector representations for semantic search.

Structured Extraction

Longer description goes here, should span multiple lines.

Invoice data extraction

Automate pulling key information from financial documents and invoices at scale.

Website data extraction

Crawl millions of web pages and extract analytics-ready datasets for your company or your customers.

Document summarization

Condense large volumes of text into concise summaries for faster analysis.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights.

RAG data preparation

Easily convert large corpuses of free-form text into vector representations for semantic search.

FAQ

What is Sutro?

What types of workflows can I run on Sutro?

How does Sutro help reduce costs?

Does Sutro integrate with my existing data stack?

How do I get started?

What Will You Scale with Sutro?

Get Access

Blog

Privacy Policy

Terms of Service

Documentation

Docs

team@sutro.sh