Supported models

SGLang supports model families across text generation, retrieval, and reward workflows. Browse the sections below for the primary product paths and jump to the detail pages when you are ready to explore a specific class.

Text generation

<CardGroup cols={3}> <Card title="Large language models" mode="card" className="max-w-sm mx-auto" href="./supported-models/generative_models" img="/cards/LLM-card.png" > Production-tuned Llama and Qwen families validated for high-throughput serving. </Card> <Card title="Vision language models" mode="card" className="max-w-sm mx-auto" href="./supported-models/multimodal_language_models" img="/cards/VLM-card.png" > Vision-text hybrids that stay responsive on multi-GPU setups. </Card> <Card title="Diffusion language models" mode="card" className="max-w-sm mx-auto" href="./sglang-diffusion/index" img="/cards/dLLM-card.png" > Score-based and diffusion backbones for structured text generation workflows. </Card> </CardGroup>

Retrieval and ranking

<CardGroup cols={3}> <Card title="Embedding models" mode="card" className="max-w-sm mx-auto" href="./supported-models/embedding_models" img="/cards/Embedding-card.png" > Dense and sparse embeddings optimized with FlashInfer kernels. </Card> <Card title="Rerank models" mode="card" className="max-w-sm mx-auto" href="./supported-models/rerank_models" img="/cards/Rerank-card.png" > Low-latency rerankers for multi-stage retrieval pipelines. </Card> <Card title="Classification models" mode="card" className="max-w-sm mx-auto" href="./supported-models/classify_models" img="/cards/Classification-card.png" > Lightweight classifiers covering safety, intent, and context filters. </Card> </CardGroup>

Specialized models

<CardGroup cols={3}> <Card title="Reward models" mode="card" className="max-w-sm mx-auto" href="./supported-models/reward_models" img="/cards/Reward-card.png" > RLHF and reward scoring pipelines optimized for production latency. </Card> </CardGroup>