# Yotta Labs

## Yotta Labs

- [About](https://docs.yottalabs.ai/company/readme.md): Welcome to Yotta Labs, where we enable enterprises and AI-native teams to deploy inference and selective training workloads efficiently, without being locked into a single cloud provider or hardware.
- [Mission](https://docs.yottalabs.ai/company/mission.md)
- [FAQs](https://docs.yottalabs.ai/company/faqs.md)
- [Getting Started](https://docs.yottalabs.ai/company/faqs/getting-started.md)
- [Billing & Pricing](https://docs.yottalabs.ai/company/faqs/billing-and-pricing.md)
- [Compute](https://docs.yottalabs.ai/company/faqs/compute.md)
- [Support & Resources](https://docs.yottalabs.ai/company/faqs/support-and-resources.md)
- [Platform Features](https://docs.yottalabs.ai/company/faqs/platform-features.md)
- [Quickstart](https://docs.yottalabs.ai/products/quickstart.md)
- [GPU Pods](https://docs.yottalabs.ai/products/gpu-pods.md): Pods are the core compute units on Yotta Platform. They allow users to deploy, manage, and connect to isolated GPU workloads across various hardware through the Console or the API interface.
- [Serverless](https://docs.yottalabs.ai/products/serverless.md)
- [Service Mode](https://docs.yottalabs.ai/products/serverless/service-mode.md)
- [Launching Serverless Tasks](https://docs.yottalabs.ai/products/serverless/launching-serverless-tasks.md)
- [Managing Serverless Tasks](https://docs.yottalabs.ai/products/serverless/managing-serverless-tasks.md)
- [Accessing Serverless Tasks](https://docs.yottalabs.ai/products/serverless/accessing-serverless-tasks.md)
- [Editing Settings](https://docs.yottalabs.ai/products/serverless/editing-settings.md)
- [Scaling Workers](https://docs.yottalabs.ai/products/serverless/scaling-workers.md)
- [Pricing & Billing](https://docs.yottalabs.ai/products/serverless/pricing-and-billing.md)
- [Queue-based](https://docs.yottalabs.ai/products/serverless/queue-based.md)
- [Launch Templates](https://docs.yottalabs.ai/products/launch-templates.md)
- [Custom Images](https://docs.yottalabs.ai/products/custom-images.md)
- [Virtual Machines](https://docs.yottalabs.ai/products/virtual-machines.md)
- [Launching a Virtual Machine](https://docs.yottalabs.ai/products/virtual-machines/launching-a-virtual-machine.md)
- [Mounting Block Volume](https://docs.yottalabs.ai/products/virtual-machines/mounting-block-volume.md)
- [Quantization](https://docs.yottalabs.ai/products/quantization.md)
- [Storage](https://docs.yottalabs.ai/products/storage.md)
- [Buckets](https://docs.yottalabs.ai/products/storage/buckets.md)
- [Volumes](https://docs.yottalabs.ai/products/storage/volumes.md)
- [AI Gateway](https://docs.yottalabs.ai/products/ai-gateway.md): If you've ever wished you could try out the latest AI models — text generation, image synthesis, video creation — without having to juggle five different API keys, five different docs, and five differ
- [Pricing](https://docs.yottalabs.ai/products/ai-gateway/pricing.md)
- [AI Explorer](https://docs.yottalabs.ai/products/ai-explorer.md)
- [Text Generation](https://docs.yottalabs.ai/products/ai-explorer/text-generation.md): Yotta Labs AI Explorer - Text Generation, a powerful and flexible platform designed for text generation tasks. Easily generate custom text content by selecting from multiple advanced models and fine-t
- [Image Generation](https://docs.yottalabs.ai/products/ai-explorer/image-generation.md): Yotta Labs AI Explorer - Image Generation is a powerful platform that allows you to create images from textual descriptions. With advanced AI models, you can transform your ideas into unique visuals,
- [Audio Generation](https://docs.yottalabs.ai/products/ai-explorer/audio-generation.md)
- [Pricing](https://docs.yottalabs.ai/products/ai-explorer/pricing.md)
- [Inference](https://docs.yottalabs.ai/products/inference.md)
- [Serverless Inference with LLM](https://docs.yottalabs.ai/products/inference/serverless-inference-with-llm.md)
- [Serverless Inference with Image Generation models](https://docs.yottalabs.ai/products/inference/serverless-inference-with-image-generation-models.md)
- [User Interface](https://docs.yottalabs.ai/products/inference/user-interface.md)
- [Broker Node](https://docs.yottalabs.ai/products/inference/broker-node.md)
- [GPU Worker](https://docs.yottalabs.ai/products/inference/gpu-worker.md)
- [Quickstart](https://docs.yottalabs.ai/products/inference/gpu-worker/quickstart.md): This document provides a high-level overview of how users can set up GPU workers to join the Yotta network.
- [Core Concept](https://docs.yottalabs.ai/products/inference/gpu-worker/core-concept.md)
- [Troubleshoot](https://docs.yottalabs.ai/products/inference/gpu-worker/troubleshoot.md)
- [Supported Devices](https://docs.yottalabs.ai/products/inference/gpu-worker/supported-devices.md)
- [FAQs](https://docs.yottalabs.ai/products/inference/gpu-worker/faqs.md): Coming soon...
- [Fine-Tune](https://docs.yottalabs.ai/products/fine-tune.md)
- [Agent](https://docs.yottalabs.ai/products/agent.md)
- [Referrals](https://docs.yottalabs.ai/products/reference-program.md)
- [Billing](https://docs.yottalabs.ai/products/billing.md): Yotta Labs provides a simple and secure way to top up your account credit, enabling uninterrupted access to advanced features like GPU instances, AI models, and more. Recharge your credit to continue
- [API Keys](https://docs.yottalabs.ai/api-and-sdk/api-keys.md)
- [API Guides](https://docs.yottalabs.ai/api-and-sdk/api-guides.md): Learn how to use Yotta’s APIs to manage GPUs, deploy workloads, and automate infrastructure.
- [Get started](https://docs.yottalabs.ai/api-and-sdk/api-guides/get-started.md): Start here with examples through api workflow listed below!
- [Pods](https://docs.yottalabs.ai/api-and-sdk/api-guides/pods.md)
- [Data Model](https://docs.yottalabs.ai/api-and-sdk/api-guides/data-model.md)
- [Serverless](https://docs.yottalabs.ai/api-and-sdk/api-guides/serverless.md)
- [Queue-based Serverless Execution](https://docs.yottalabs.ai/api-and-sdk/api-guides/serverless/queue-based-elastic-execution.md)
- [Credential](https://docs.yottalabs.ai/api-and-sdk/api-guides/credential.md)
- [Virtual Machines](https://docs.yottalabs.ai/api-and-sdk/api-guides/virtual-machines.md)
- [Volume](https://docs.yottalabs.ai/api-and-sdk/api-guides/volume.md)
- [API Reference - v1](https://docs.yottalabs.ai/api-and-sdk/api-reference-v1.md)
- [Credentials](https://docs.yottalabs.ai/api-and-sdk/api-reference-v1/credentials.md)
- [Pods](https://docs.yottalabs.ai/api-and-sdk/api-reference-v1/pods.md)
- [VMs](https://docs.yottalabs.ai/api-and-sdk/api-reference-v1/vms.md)
- [Serverless](https://docs.yottalabs.ai/api-and-sdk/api-reference-v1/serverless.md)
- [API Reference - v2](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2.md)
- [Credentials](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/credentials.md)
- [Pods](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/pods.md)
- [VMs](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/vms.md)
- [Serverless](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/serverless.md)
- [Metrics](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/metrics.md)
- [Reserves](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/reserves.md)
- [Volume](https://docs.yottalabs.ai/api-and-sdk/api-reference-v2/volume.md)
- [Platform Setup](https://docs.yottalabs.ai/tutorials/platform-setup.md)
- [How to Build Custom Images](https://docs.yottalabs.ai/tutorials/platform-setup/how-to-build-custom-images.md)
- [Training & Fine-tuning](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning.md)
- [Get Started in LLM Training with Pytorch 2.8.0](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/get-started-in-llm-training-with-pytorch-2.8.0.md)
- [Accelerating PyTorch Training with TorchDynamo and JIT](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/accelerating-pytorch-training-with-torchdynamo-and-jit.md)
- [Fine-tuning Orpheus\_(3B)-TTS with Unsloth](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/fine-tuning-orpheus_-3b-tts-with-unsloth.md)
- [GRPO on GSM8K with SkyRL](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/grpo-on-gsm8k-with-virtual-machine.md)
- [GRPO on MathVista with Unsloth](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/grpo-on-mathvista-with-unsloth.md)
- [Fine-tune a Reasoning Model to Think in Target Language with Unsloth](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/fine-tune-a-reasoning-model-to-think-in-target-language-with-unsloth.md)
- [SkyRL for LLM-as-a-Judge Training](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/skyrl-for-llm-as-a-judge-training.md)
- [Reinforced Learning with Miles](https://docs.yottalabs.ai/tutorials/training-and-fine-tuning/reinforced-learning-with-miles.md)
- [Inference & Serving](https://docs.yottalabs.ai/tutorials/inference-and-serving.md)
- [Guide to Serverless](https://docs.yottalabs.ai/tutorials/inference-and-serving/guide-to-serverless.md)
- [Queue-based Serverless Quickstart](https://docs.yottalabs.ai/tutorials/inference-and-serving/queue-based-serverless-quickstart.md)
- [LLM Serving on Yotta Labs with AWS Trainium](https://docs.yottalabs.ai/tutorials/inference-and-serving/llm-serving-on-yotta-labs-with-aws-trainium.md)
- [Running DFlash with Qwen3.6-35B-A3B on RTX PRO 6000](https://docs.yottalabs.ai/tutorials/inference-and-serving/running-dflash-with-qwen3.6-35b-a3b-on-rtx-pro-6000.md)
- [Run DeepSeek V4 Flash/Pro on B300](https://docs.yottalabs.ai/tutorials/inference-and-serving/run-deepseek-v4-flash-pro-on-b300.md)
- [Image & Video Generation](https://docs.yottalabs.ai/tutorials/image-and-video-generation.md)
- [Generating Images with Z-Image Model Quickstart](https://docs.yottalabs.ai/tutorials/image-and-video-generation/generating-images-with-z-image-model-quickstart.md)
- [Generate Product Images with Wan2.1/2.2](https://docs.yottalabs.ai/tutorials/image-and-video-generation/generate-product-images-with-wan2.1-2.2.md)
- [Image Generation with FLUX.1-dev](https://docs.yottalabs.ai/tutorials/image-and-video-generation/image-generation-with-flux.1-dev.md)
- [Video Generation with ComfyUI](https://docs.yottalabs.ai/tutorials/image-and-video-generation/video-generation-with-comfyui.md)
- [Video Generation with ComfyUI-nunchaku](https://docs.yottalabs.ai/tutorials/image-and-video-generation/video-generation-with-comfyui-nunchaku.md)
- [Quant-VideoGen on RTX 5090](https://docs.yottalabs.ai/tutorials/image-and-video-generation/quant-videogen-on-rtx-5090.md)
- [Sparse-VideoGen on NVIDIA H200](https://docs.yottalabs.ai/tutorials/image-and-video-generation/sparse-videogen-on-nvidia-h200.md)
- [3DGRUT on A100: Build your own 3D Scene Reconstruction](https://docs.yottalabs.ai/tutorials/image-and-video-generation/3dgrut-on-a100-build-your-own-3d-scene-reconstruction.md)
- [Sol-RL on A100: Post-Training Diffusion Models at the Speed of Light](https://docs.yottalabs.ai/tutorials/image-and-video-generation/sol-rl-on-a100-post-training-diffusion-models-at-the-speed-of-light.md)
- [SANA-WM: Deploying NVIDIA's World Model on a Single RTX Pro 6000](https://docs.yottalabs.ai/tutorials/image-and-video-generation/sana-wm-deploying-nvidias-world-model-on-a-single-rtx-pro-6000.md)
- [AI Agents](https://docs.yottalabs.ai/tutorials/ai-agents.md)
- [NemoClaw with Local Inference](https://docs.yottalabs.ai/tutorials/ai-agents/nemoclaw-with-local-inference.md)
- [Buiding Your Own Chatbot in Feishu with Openclaw-lite](https://docs.yottalabs.ai/tutorials/ai-agents/buiding-your-own-chatbot-in-feishu-with-openclaw-lite.md)
- [Start Your Local Openclaw Bot with 1 Click](https://docs.yottalabs.ai/tutorials/ai-agents/start-your-local-openclaw-bot-with-1-click.md)
- [SkyPilot](https://docs.yottalabs.ai/tutorials/skypilot.md)
- [Getting started with YottaLabs on SkyPilot](https://docs.yottalabs.ai/tutorials/skypilot/getting-started-with-yottalabs-on-skypilot.md): Run your first GPU job
- [Training a simple MNIST model on YottaLabs with SkyPilot](https://docs.yottalabs.ai/tutorials/skypilot/training-a-simple-mnist-model-on-yottalabs-with-skypilot.md)
- [Parallelism Strategies](https://docs.yottalabs.ai/technology/parallelism-strategies.md)
- [Decentralized Scheduling](https://docs.yottalabs.ai/technology/decentralized-scheduling.md)
- [Memory Optimization](https://docs.yottalabs.ai/technology/memory-optimization.md)
- [Proactive Communication](https://docs.yottalabs.ai/technology/proactive-communication.md)
- [Fault Tolerance](https://docs.yottalabs.ai/technology/fault-tolerance.md)
- [Computation Validation](https://docs.yottalabs.ai/technology/computation-validation.md)
- [Overview](https://docs.yottalabs.ai/tokenomics/overview.md)
- [Payment & Fee](https://docs.yottalabs.ai/tokenomics/payment-and-fee.md)
- [Staking](https://docs.yottalabs.ai/tokenomics/staking.md)
- [GPU Incentive](https://docs.yottalabs.ai/tokenomics/gpu-incentive.md)
- [Community](https://docs.yottalabs.ai/tokenomics/community.md)
- [Governance](https://docs.yottalabs.ai/tokenomics/governance.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.yottalabs.ai/company/readme.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.