minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

docs: sync LMSYS SGLang blog cards (#35416)

Browse Source 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
This commit is contained in:
sglang-bot
2026-08-27 03:56:54 +00:00
committed by GitHub
co-authored by sglang-bot
parent 02dfd37826
commit e6c1a3cd4c
1 changed files with 30 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/index.mdx
+30 -30
View File
@@ -90,7 +90,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<a
href="https://lmsys.org/blog/2026-08-17-advanced-cuda-graph/"
href="https://lmsys.org/blog/2026-08-26-qwen-flash-next/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -111,8 +111,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/breakable_cuda_graph/bcg-design.svg"
alt="Advanced CUDA Graph Techniques in SGLang"
src="https://lmsys.org/images/blog/qwen-flash-next/cover.png"
alt="Qwen3.8-Flash-Next: Day-0 Support in SGLang"
style={{
width: "100%",
height: "100%",
@@ -131,7 +131,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"Advanced CUDA Graph Techniques in SGLang"}
{"Qwen3.8-Flash-Next: Day-0 Support in SGLang"}
</p>
<p
style={{
@@ -140,12 +140,12 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"August 17, 2026"}
{"August 26, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-12-qwen3-8-day0-support/"
href="https://lmsys.org/blog/2026-08-21-sglang-fast-recovery/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -166,8 +166,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/qwen3-8-day0-support/cover-qwen3-8.png"
alt="SGLang and Miles Add Day-0 Support for Qwen3.8"
src="https://lmsys.org/images/blog/sglang-fast-recovery/preview.png"
alt="Fast Engine Recovery: Sub-Second Engine Restart for SGLang via Weight Cache Daemon"
style={{
width: "100%",
height: "100%",
@@ -186,7 +186,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"SGLang and Miles Add Day-0 Support for Qwen3.8"}
{"Fast Engine Recovery: Sub-Second Engine Restart for SGLang via Weight Cache Daemon"}
</p>
<p
style={{
@@ -195,12 +195,12 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"Aug 12, 2026"}
{"August 21, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-11-unified-radix-cache/"
href="https://lmsys.org/blog/2026-08-21-ling3-flash-spec-decode-blackwell/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -221,8 +221,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/unified-radix-cache/image1.svg"
alt="Unified Radix Cache: One Tree for Hybrid Model Prefix Caching"
src="https://lmsys.org/images/blog/ling3-flash-batch1/00_headline.png"
alt="Chasing the Batch-1 Floor: Ling-3.0-flash Speculative Decode on Blackwell"
style={{
width: "100%",
height: "100%",
@@ -241,7 +241,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"Unified Radix Cache: One Tree for Hybrid Model Prefix Caching"}
{"Chasing the Batch-1 Floor: Ling-3.0-flash Speculative Decode on Blackwell"}
</p>
<p
style={{
@@ -250,12 +250,12 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"August 11, 2026"}
{"August 21, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-11-nemotron-3-5-lightning/"
href="https://lmsys.org/blog/2026-08-20-miles-mooncake-rollout-data-transfer/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -276,8 +276,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/nemotron-3-5-lightning/pinchbench-accuracy-vs-time.png"
alt="SGLang Adds Day-0 Support for NVIDIA Nemotron 3.5 Lightning"
src="https://lmsys.org/images/blog/miles-mooncake-rollout-data-transfer/featured.png"
alt="Mooncake for Miles: From Fragmented Rollout Data to Efficient Bulk I/O"
style={{
width: "100%",
height: "100%",
@@ -296,7 +296,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"SGLang Adds Day-0 Support for NVIDIA Nemotron 3.5 Lightning"}
{"Mooncake for Miles: From Fragmented Rollout Data to Efficient Bulk I/O"}
</p>
<p
style={{
@@ -305,12 +305,12 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"August 11, 2026"}
{"August 20, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-10-meta-muse-glimmer/"
href="https://lmsys.org/blog/2026-08-19-deepseek-v4-pro-engine-optimization-h20/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -331,8 +331,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/2026-08-10-meta-muse-glimmer/cover-muse-glimmer.png"
alt="SGLang Adds Day-0 Support for Muse Glimmer, a Multimodal Model Built for Local Agentic Workflows"
src="https://lmsys.org/images/blog/deepseek_v4/00_cover.png"
alt="Pushing the Limits of Serving DeepSeek-V4-Pro"
style={{
width: "100%",
height: "100%",
@@ -351,7 +351,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"SGLang Adds Day-0 Support for Muse Glimmer, a Multimodal Model Built for Local Agentic Workflows"}
{"Pushing the Limits of Serving DeepSeek-V4-Pro"}
</p>
<p
style={{
@@ -360,12 +360,12 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"August 10, 2026"}
{"August 19, 2026"}
</p>
</div>
</a>
<a
href="https://lmsys.org/blog/2026-08-07-hpc-ops-sglang/"
href="https://lmsys.org/blog/2026-08-18-miles-v0-1/"
target="_blank"
rel="noopener noreferrer"
style={{
@@ -386,8 +386,8 @@ It is designed to deliver low-latency and high-throughput inference across a wid
}}
>
<img
src="https://lmsys.org/images/blog/hpc-ops-sglang/hpc-ops-sglang-cover.webp"
alt="HPC-Ops \u00d7 SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan"
src="https://lmsys.org/images/blog/miles-v0-1/miles-logo.png"
alt="Miles v0.1: Production-level Post-training"
style={{
width: "100%",
height: "100%",
@@ -406,7 +406,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
fontSize: "0.98rem",
}}
>
{"HPC-Ops \u00d7 SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan"}
{"Miles v0.1: Production-level Post-training"}
</p>
<p
style={{
@@ -415,7 +415,7 @@ It is designed to deliver low-latency and high-throughput inference across a wid
opacity: 0.75,
}}
>
{"August 7, 2026"}
{"August 18, 2026"}
</p>
</div>
</a>