Skip to main content

Ctrl+K

Overview

FuriosaAI RNGD
FuriosaAI’s Software Stack
What’s New
Roadmap

Get Started

Installing Prerequisites
Quick Start with Furiosa-LLM
Upgrading FuriosaAI’s Software

Furiosa-LLM

Furiosa-LLM
Supported Models
- Qwen3 (dense)
- Qwen3-MoE
- BGE-M3
- E5-Mistral
- BGE Reranker v2 M3
- Harrier OSS v1
- Qwen3-Embedding
- Qwen3-Reranker
- Qwen3-VL
- Gemma 4
- Qwen2.5
- Llama 3.1
- Llama 3.3
- Mistral NeMo
- GPT-OSS
- EXAONE 4.0
- EXAONE 4.5
- K-EXAONE
- Solar Open
OpenAI-Compatible Server
Responses API
Tool Calling
Structured Output
Vision-Language Models
Prefix Caching
Hierarchical Prefix Caching
Hybrid KV Cache Management
Data-Parallel Routing
Furiosa Executable Bundles (FXB)
Model Parallelism
API Reference
Examples
Deploying Furiosa-LLM on Kubernetes
Using Mooncake with Furiosa-LLM

Cloud Native Toolkit

Cloud Native Toolkit
Container Support
Kubernetes Plugins
Deploying Furiosa-LLM with llm-d

Device Management

Furiosa SMI
- Furiosa SMI CLI
- Furiosa SMI Library
Host PCI Optimization Tuning

Tutorials and Examples

FuriosaAI SDK CookBook

Customer Support

Forums
Customer Support

Other Links

FuriosaAI Homepage
Furiosa Gen 1 NPU SDK Doc

© Copyright 2026 FuriosaAI Inc.

API Reference

API Reference#

API Reference

LLM class
SamplingParams class
PoolingParams class
LLMEngine class
AsyncLLMEngine class

previous

Model Parallelism

next

LLM class

By FuriosaAI, Inc.

© Copyright 2026 FuriosaAI Inc.