docs: sync LMSYS SGLang blog cards (#27322)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
This commit is contained in:
sglang-bot
+220
-220
@@ -82,6 +82,226 @@ It is designed to deliver low-latency and high-throughput inference across a wid
|
|||||||
alignItems: "stretch",
|
alignItems: "stretch",
|
||||||
}}
|
}}
|
||||||
>
|
>
|
||||||
|
<a
|
||||||
|
href="https://lmsys.org/blog/2026-06-04-nvidia-run-nemotron-3-ultra/"
|
||||||
|
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/nemotron-3-ultra/image1.png"
|
||||||
|
alt="SGLang and Miles Add Day-0 Support for NVIDIA Nemotron 3 Ultra for Long-Running Autonomous Agents"
|
||||||
|
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",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"SGLang and Miles Add Day-0 Support for NVIDIA Nemotron 3 Ultra for Long-Running Autonomous Agents"}
|
||||||
|
</p>
|
||||||
|
<p
|
||||||
|
style={{
|
||||||
|
margin: "0.55rem 0 0",
|
||||||
|
fontSize: "0.85rem",
|
||||||
|
opacity: 0.75,
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"June 4, 2026"}
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
</a>
|
||||||
|
<a
|
||||||
|
href="https://lmsys.org/blog/2026-06-04-higgs-audio-v3-tts/"
|
||||||
|
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://sgl-project.github.io/sglang-omni/_images/higgs-architecture.png"
|
||||||
|
alt="Higgs Audio v3 TTS on SGLang-Omni: Real-Time, Controllable Speech for Voice Agents"
|
||||||
|
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",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"Higgs Audio v3 TTS on SGLang-Omni: Real-Time, Controllable Speech for Voice Agents"}
|
||||||
|
</p>
|
||||||
|
<p
|
||||||
|
style={{
|
||||||
|
margin: "0.55rem 0 0",
|
||||||
|
fontSize: "0.85rem",
|
||||||
|
opacity: 0.75,
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"June 4, 2026"}
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
</a>
|
||||||
|
<a
|
||||||
|
href="https://lmsys.org/blog/2026-06-01-hetero-epd/"
|
||||||
|
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/hetero-epd/1.png"
|
||||||
|
alt="Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving"
|
||||||
|
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",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving"}
|
||||||
|
</p>
|
||||||
|
<p
|
||||||
|
style={{
|
||||||
|
margin: "0.55rem 0 0",
|
||||||
|
fontSize: "0.85rem",
|
||||||
|
opacity: 0.75,
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"May 29, 2026"}
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
</a>
|
||||||
|
<a
|
||||||
|
href="https://lmsys.org/blog/2026-05-28-mori/"
|
||||||
|
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/mori/tco1-new.png"
|
||||||
|
alt="Win on TCO: How AMD Instinct\u2122 MI355X Achieves Cost-Competitive Distributed Inference Through SGLang with MoRI"
|
||||||
|
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",
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"Win on TCO: How AMD Instinct\u2122 MI355X Achieves Cost-Competitive Distributed Inference Through SGLang with MoRI"}
|
||||||
|
</p>
|
||||||
|
<p
|
||||||
|
style={{
|
||||||
|
margin: "0.55rem 0 0",
|
||||||
|
fontSize: "0.85rem",
|
||||||
|
opacity: 0.75,
|
||||||
|
}}
|
||||||
|
>
|
||||||
|
{"May 28, 2026"}
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
</a>
|
||||||
<a
|
<a
|
||||||
href="https://lmsys.org/blog/2026-04-29-p2p-update/"
|
href="https://lmsys.org/blog/2026-04-29-p2p-update/"
|
||||||
target="_blank"
|
target="_blank"
|
||||||
@@ -192,226 +412,6 @@ It is designed to deliver low-latency and high-throughput inference across a wid
|
|||||||
</p>
|
</p>
|
||||||
</div>
|
</div>
|
||||||
</a>
|
</a>
|
||||||
<a
|
|
||||||
href="https://lmsys.org/blog/2026-04-10-sglang-hisparse/"
|
|
||||||
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/hisparse/hisparse_overview.png"
|
|
||||||
alt="HiSparse: Turbocharging Sparse Attention with Hierarchical Memory"
|
|
||||||
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",
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"HiSparse: Turbocharging Sparse Attention with Hierarchical Memory"}
|
|
||||||
</p>
|
|
||||||
<p
|
|
||||||
style={{
|
|
||||||
margin: "0.55rem 0 0",
|
|
||||||
fontSize: "0.85rem",
|
|
||||||
opacity: 0.75,
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"April 10, 2026"}
|
|
||||||
</p>
|
|
||||||
</div>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://lmsys.org/blog/2026-03-25-gtc2026/"
|
|
||||||
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/gtc2026/happyhour-crowd.jpg"
|
|
||||||
alt="Highlights of SGLang at NVIDIA GTC 2026"
|
|
||||||
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",
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"Highlights of SGLang at NVIDIA GTC 2026"}
|
|
||||||
</p>
|
|
||||||
<p
|
|
||||||
style={{
|
|
||||||
margin: "0.55rem 0 0",
|
|
||||||
fontSize: "0.85rem",
|
|
||||||
opacity: 0.75,
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"March 31, 2026"}
|
|
||||||
</p>
|
|
||||||
</div>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://lmsys.org/blog/2026-03-25-eep-partial-failure-tolerance/"
|
|
||||||
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/eep-partial-failure-tolerance/figure.png"
|
|
||||||
alt="Elastic EP in SGLang: Achieving Partial Failure Tolerance for DeepSeek MoE Deployments"
|
|
||||||
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",
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"Elastic EP in SGLang: Achieving Partial Failure Tolerance for DeepSeek MoE Deployments"}
|
|
||||||
</p>
|
|
||||||
<p
|
|
||||||
style={{
|
|
||||||
margin: "0.55rem 0 0",
|
|
||||||
fontSize: "0.85rem",
|
|
||||||
opacity: 0.75,
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"March 25, 2026"}
|
|
||||||
</p>
|
|
||||||
</div>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://lmsys.org/blog/2026-03-17-rocm-miles-rl-amd/"
|
|
||||||
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/rocm_miles_rl/fig_1.png"
|
|
||||||
alt="ROCm Support for Miles: Large-Scale RL Post-Training on AMD Instinct\u2122 GPUs"
|
|
||||||
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",
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"ROCm Support for Miles: Large-Scale RL Post-Training on AMD Instinct\u2122 GPUs"}
|
|
||||||
</p>
|
|
||||||
<p
|
|
||||||
style={{
|
|
||||||
margin: "0.55rem 0 0",
|
|
||||||
fontSize: "0.85rem",
|
|
||||||
opacity: 0.75,
|
|
||||||
}}
|
|
||||||
>
|
|
||||||
{"March 17, 2026"}
|
|
||||||
</p>
|
|
||||||
</div>
|
|
||||||
</a>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
{/* END_LMSYS_SGLANG_BLOG_CARDS */}
|
{/* END_LMSYS_SGLANG_BLOG_CARDS */}
|
||||||
|
|||||||
Reference in New Issue
Block a user