docs: sync LMSYS SGLang blog cards (#30571)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
This commit is contained in:
sglang-bot
+110
-110
@@ -82,6 +82,61 @@ It is designed to deliver low-latency and high-throughput inference across a wid
|
||||
alignItems: "stretch",
|
||||
}}
|
||||
>
|
||||
<a
|
||||
href="https://lmsys.org/blog/2026-07-10-rocm-miles-dsv4/"
|
||||
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-dsv4/preview.png"
|
||||
alt="Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles"
|
||||
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",
|
||||
}}
|
||||
>
|
||||
{"Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles"}
|
||||
</p>
|
||||
<p
|
||||
style={{
|
||||
margin: "0.55rem 0 0",
|
||||
fontSize: "0.85rem",
|
||||
opacity: 0.75,
|
||||
}}
|
||||
>
|
||||
{"July 10, 2026"}
|
||||
</p>
|
||||
</div>
|
||||
</a>
|
||||
<a
|
||||
href="https://lmsys.org/blog/2026-07-06-dspark-sglang/"
|
||||
target="_blank"
|
||||
@@ -192,6 +247,61 @@ It is designed to deliver low-latency and high-throughput inference across a wid
|
||||
</p>
|
||||
</div>
|
||||
</a>
|
||||
<a
|
||||
href="https://lmsys.org/blog/2026-06-27-netpreme-xmem/"
|
||||
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/netpreme-xmem/figure1.png"
|
||||
alt="Accelerating SGLang HiCache with Netpreme X-Mem\u2122 MPU"
|
||||
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",
|
||||
}}
|
||||
>
|
||||
{"Accelerating SGLang HiCache with Netpreme X-Mem\u2122 MPU"}
|
||||
</p>
|
||||
<p
|
||||
style={{
|
||||
margin: "0.55rem 0 0",
|
||||
fontSize: "0.85rem",
|
||||
opacity: 0.75,
|
||||
}}
|
||||
>
|
||||
{"July 8, 2026"}
|
||||
</p>
|
||||
</div>
|
||||
</a>
|
||||
<a
|
||||
href="https://lmsys.org/blog/2026-06-26-waterfill-lplb/"
|
||||
target="_blank"
|
||||
@@ -302,116 +412,6 @@ It is designed to deliver low-latency and high-throughput inference across a wid
|
||||
</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 */}
|
||||
|
||||
Reference in New Issue
Block a user