Files
wehub-resource-sync 94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

498 lines
14 KiB
Plaintext

---
title: Welcome to SGLang
description: High-performance serving framework for large language and multimodal models.
keywords:
- sglang
- llm serving
- multimodal
- inference runtime
mode: wide
---
<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></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](https://lmsys.org/about/).
---
## Get Started
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>
## News and latest blogs
{/* BEGIN_LMSYS_SGLANG_BLOG_CARDS */}
<div className="not-prose">
<div
style={{
display: "grid",
gridTemplateColumns: "repeat(auto-fit, minmax(300px, 1fr))",
gap: "1rem",
alignItems: "stretch",
}}
>
<a
href="https://lmsys.org/blog/2026-07-06-dspark-sglang/"
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)",
}}
>
<img
src="https://lmsys.org/images/blog/dspark-sglang/perf-compare.png"
alt="DSpark in SGLang: Speculative Decoding with Confidence-Driven, Variable-Length Verification"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"DSpark in SGLang: Speculative Decoding with Confidence-Driven, Variable-Length Verification"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"July 6, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-07-02-agent-assisted-sglang-development/"
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)",
}}
>
<img
src="https://lmsys.org/images/blog/agent-assisted-sglang-development/sglang-agent-cover.png"
alt="Agent-Assisted SGLang Development: An Initial Exploration"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Agent-Assisted SGLang Development: An Initial Exploration"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"July 2, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-06-26-waterfill-lplb/"
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)",
}}
>
<img
src="https://lmsys.org/images/blog/waterfill_lplb/waterfill_timeline_nature_redraw.png"
alt="Improving DeepEP MoE Load Balance in SGLang with Waterfill and LPLB"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Improving DeepEP MoE Load Balance in SGLang with Waterfill and LPLB"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"June 26, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-06-17-moss-tts-local-v15/"
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)",
}}
>
<img
src="https://raw.githubusercontent.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/main/sglang/sglang-omni/images/moss-local-transformer-arch.svg"
alt="MOSS-TTS Local Transformer v1.5 on SGLang-Omni: Serving Native-Streaming 48 kHz Speech"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"MOSS-TTS Local Transformer v1.5 on SGLang-Omni: Serving Native-Streaming 48 kHz Speech"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"June 17, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-06-17-ling-2-6-tpu/"
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)",
}}
>
<img
src="https://lmsys.org/images/blog/2026-06-17-ling-2-6-tpu/hero.png"
alt="Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"June 17, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-06-15-next-generation-speculative-decoding-dflash-v2/"
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)",
}}
>
<img
src="https://lmsys.org/images/blog/dflash-v2/dflash-arch-diagram.webp"
alt="The next generation of speculative decoding: DFlash and Spec V2"
style={{
width: "100%",
height: "100%",
objectFit: "cover",
objectPosition: "center",
display: "block",
}}
/>
</div>
<div style={{ padding: "0.9rem 1rem 1rem" }}>
<p
style={{
margin: 0,
fontWeight: 600,
lineHeight: 1.35,
fontSize: "0.98rem",
}}
>
{"The next generation of speculative decoding: DFlash and Spec V2"}
</p>
<p
style={{
margin: "0.55rem 0 0",
fontSize: "0.85rem",
opacity: 0.75,
}}
>
{"June 15, 2026"}
</p>
</div>
</a>
</div>
</div>
{/* END_LMSYS_SGLANG_BLOG_CARDS */}
---
## Learn more and join the community
<div className="not-prose">
<div
style={{
padding: "0.9rem 0",
borderTop: "1px solid rgba(128, 128, 128, 0.24)",
borderBottom: "1px solid rgba(128, 128, 128, 0.24)",
}}
>
<p
style={{
margin: "0 0 0.35rem",
fontSize: "0.82rem",
fontWeight: 700,
letterSpacing: "0.08em",
textTransform: "uppercase",
opacity: 0.72,
}}
>
Stay connected
</p>
<div
style={{
display: "grid",
gap: "0.55rem",
fontSize: "0.97rem",
lineHeight: 1.7,
}}
>
<div>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="map" size={14} />
</span>{" "}
<a href="https://roadmap.sglang.io">Development roadmap</a>
<span style={{ opacity: 0.62 }}> to follow current priorities and upcoming work.</span>
</div>
<div>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="calendar-days" size={14} />
</span>{" "}
<a href="https://meet.sglang.io">Weekly public development meeting</a>
<span style={{ opacity: 0.62 }}> to hear updates and join open discussions.</span>
</div>
<div>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="slack" size={14} />
</span>{" "}
<a href="https://slack.sglang.io/">Slack</a>
<span style={{ opacity: 0.62 }}> for questions, feedback, and community support.</span>
</div>
<div>
<a href="https://x.com/lmsysorg">X Twitter</a>
<span style={{ opacity: 0.62 }}> and </span>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="linkedin" size={14} />
</span>{" "}
<a href="https://www.linkedin.com/company/sgl-project/">LinkedIn</a>
<span style={{ opacity: 0.62 }}> for project updates.</span>
</div>
<div>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="newspaper" size={14} />
</span>{" "}
<a href="https://lmsys.org/blog/">LMSYS blog</a>
<span style={{ opacity: 0.62 }}> for release notes, benchmarks, and technical deep dives.</span>
</div>
<div>
<span style={{ display: "inline-flex", alignItems: "center", verticalAlign: "-0.125em" }}>
<Icon icon="book-open" size={14} />
</span>{" "}
<a href="https://github.com/sgl-project/sgl-learning-materials">Learning materials</a>
<span style={{ opacity: 0.62 }}> for blogs, slides, and videos.</span>
</div>
</div>
</div>
</div>