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…

Embedding Generation

Easily Create Vector Embeddings at Massive Scale, for Less

Easily convert large corpuses of free-form text into vector representations for semantic search and recommendations. Run LLM batch jobs in hours, not days, at a fraction of the cost.

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…

From Idea to Production Embeddings, Simplified

Sutro takes the pain away from generating embeddings at scale, unblocking your most ambitious AI projects.

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 embedding workflows. Accelerate experiments by testing on Sutro before committing to large jobs.

Scale

Scale your LLM workflows to 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.

Reduce Costs by 10x or More

Get results faster and reduce costs by parallelizing your embedding generation calls through Sutro, removing the pain of managing infrastructure.

Scale Effortlessly

Scale Effortlessly

Scale Effortlessly

Confidently handle millions of requests and billions of tokens. Convert entire corpuses of free-form text into vector representations without infrastructure headaches.

Rapidly Prototype Your AI Applications

Shorten development cycles for your semantic search and RAG applications. Get feedback from large batch embedding jobs in as little as minutes before scaling up.

RAG data preparation

Longer description goes here, should span multiple lines.

Structured Extraction

Transform unstructured data into structured insights that drive business decisions.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights while brewing your morning coffee.

Document summarization

Convert your massive amounts of free-form text into analytics-ready datasets without the pains of managing your own infrastructure.

LLM performance evaluation

Benchmark your LLM outputs to continuously improve workflows, agents and assistants, or easily evaluate custom models against a new use-case.

Synthetic data generation

Generate high-quality, diverse, and representative synthetic data to improve model or RAG retrieval performance, without the complexity.

RAG data preparation

Longer description goes here, should span multiple lines.

Structured Extraction

Transform unstructured data into structured insights that drive business decisions.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights while brewing your morning coffee.

Document summarization

Convert your massive amounts of free-form text into analytics-ready datasets without the pains of managing your own infrastructure.

LLM performance evaluation

Benchmark your LLM outputs to continuously improve workflows, agents and assistants, or easily evaluate custom models against a new use-case.

Synthetic data generation

Generate high-quality, diverse, and representative synthetic data to improve model or RAG retrieval performance, without the complexity.

RAG data preparation

Longer description goes here, should span multiple lines.

Structured Extraction

Transform unstructured data into structured insights that drive business decisions.

Sentiment analysis

Easily sift through thousands of product reviews and unlock valuable product insights while brewing your morning coffee.

Document summarization

Convert your massive amounts of free-form text into analytics-ready datasets without the pains of managing your own infrastructure.

LLM performance evaluation

Benchmark your LLM outputs to continuously improve workflows, agents and assistants, or easily evaluate custom models against a new use-case.

Synthetic data generation

Generate high-quality, diverse, and representative synthetic data to improve model or RAG retrieval performance, without the complexity.

FAQ

What is Sutro?

What tasks can I perform with Sutro?

How does Sutro reduce costs?

Can I test my workflows before running a large job?

How do I integrate Sutro with my current tools?

What Will You Scale with Sutro?

Get Access

Blog

Privacy Policy

Terms of Service

Documentation

Docs

team@sutro.sh