docs/index.mdx
import { popularModels } from "/src/snippets/configs/popular-models.jsx"; import { PopularModels } from "/src/snippets/_popular_models.jsx";
{/* One hero per model, rotating. The Cookbook landing page renders the same list as a compact strip. Edit the list, not this page. */} <PopularModels models={popularModels} variant="hero" />
<a class="github-button" href="https://github.com/sgl-project/sglang" data-size="large" data-show-count="true" aria-label="Star sgl-project/sglang on GitHub"
Star </a> <a class="github-button" href="https://github.com/sgl-project/sglang/fork" data-icon="octicon-repo-forked" data-size="large" data-show-count="true" aria-label="Fork sgl-project/sglang on GitHub"
Fork </a>
<script async defer src="https://buttons.github.io/buttons.js"></script> </br> <CardGroup cols={2}> <Card title="Performance & Runtime" icon="arrow-trend-up"> Designed for low-latency, high-throughput inference with RadixAttention, prefix caching, and multi-GPU parallelism. </Card> <Card title="Models & Ecosystem" icon="hexagon-nodes"> Broad support for Llama, Qwen, DeepSeek, and more. Compatible with Hugging Face and OpenAI APIs. </Card> <Card title="Extensive Hardware Support" icon="microchip"> Native support across <a href="./docs/hardware-platforms/overview">Hardware Platforms</a> including NVIDIA, AMD, Intel Xeon, Google TPU, and Ascend NPU accelerators. </Card> <Card title="Community & Training" icon="users"> Open-source with widespread adoption, powering 400k+ GPUs and integrated with major RL frameworks. </Card> </CardGroup>SGLang powers large-scale production deployments, generating trillions of tokens each day across more than 400,000 GPUs worldwide. It is hosted under the non-profit open-source organization LMSYS.
SGLang is an inference framework meant for production level serving. It is designed to deliver low-latency and high-throughput inference across a wide range of setups, from a single GPU to large distributed clusters.
<CardGroup cols={2}> <Card title="Install SGLang" icon="angles-down" href="./docs/get-started/install"> Install SGLang with pip, from source, or via Docker on your preferred hardware platform. </Card> <Card title="Quickstart" icon="zap" href="./docs/get-started/quickstart"> Launch your first model server and send requests in minutes with OpenAI-compatible APIs. </Card> </CardGroup> </div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Qwen3.8-Flash-Next: Day-0 Support in SGLang"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 26, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-21-sglang-fast-recovery/"
target="_blank"
rel="noopener noreferrer"
style={{
display: "block",
border: "1px solid rgba(128, 128, 128, 0.3)",
borderRadius: "0.75rem",
overflow: "hidden",
textDecoration: "none",
color: "inherit",
height: "100%",
}}
>
<div
style={{
aspectRatio: "16 / 9",
overflow: "hidden",
background: "rgba(128, 128, 128, 0.15)",
}}
>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Fast Engine Recovery: Sub-Second Engine Restart for SGLang via Weight Cache Daemon"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 21, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-21-ling3-flash-spec-decode-blackwell/"
target="_blank"
rel="noopener noreferrer"
style={{
display: "block",
border: "1px solid rgba(128, 128, 128, 0.3)",
borderRadius: "0.75rem",
overflow: "hidden",
textDecoration: "none",
color: "inherit",
height: "100%",
}}
>
<div
style={{
aspectRatio: "16 / 9",
overflow: "hidden",
background: "rgba(128, 128, 128, 0.15)",
}}
>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Chasing the Batch-1 Floor: Ling-3.0-flash Speculative Decode on Blackwell"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 21, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-20-miles-mooncake-rollout-data-transfer/"
target="_blank"
rel="noopener noreferrer"
style={{
display: "block",
border: "1px solid rgba(128, 128, 128, 0.3)",
borderRadius: "0.75rem",
overflow: "hidden",
textDecoration: "none",
color: "inherit",
height: "100%",
}}
>
<div
style={{
aspectRatio: "16 / 9",
overflow: "hidden",
background: "rgba(128, 128, 128, 0.15)",
}}
>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Mooncake for Miles: From Fragmented Rollout Data to Efficient Bulk I/O"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 20, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-19-deepseek-v4-pro-engine-optimization-h20/"
target="_blank"
rel="noopener noreferrer"
style={{
display: "block",
border: "1px solid rgba(128, 128, 128, 0.3)",
borderRadius: "0.75rem",
overflow: "hidden",
textDecoration: "none",
color: "inherit",
height: "100%",
}}
>
<div
style={{
aspectRatio: "16 / 9",
overflow: "hidden",
background: "rgba(128, 128, 128, 0.15)",
}}
>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Pushing the Limits of Serving DeepSeek-V4-Pro"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 19, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-18-miles-v0-1/"
target="_blank"
rel="noopener noreferrer"
style={{
display: "block",
border: "1px solid rgba(128, 128, 128, 0.3)",
borderRadius: "0.75rem",
overflow: "hidden",
textDecoration: "none",
color: "inherit",
height: "100%",
}}
>
<div
style={{
aspectRatio: "16 / 9",
overflow: "hidden",
background: "rgba(128, 128, 128, 0.15)",
}}
>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Miles v0.1: Production-level Post-training"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"August 18, 2026"}
</p>
</div>
</a>