sglang.ai -> sglang.io

merrymercy · merrymercy · commit 09af7eee05b8 · 2025-12-28T18:07:50.000-08:00
diff --git a/blog/2025-07-08-ome.md b/blog/2025-07-08-ome.md
@@ -465,8 +465,8 @@ OME represents a paradigm shift from deployment-driven to model-driven infrastru
 
 **Get Involved:**
 - **GitHub**: [github.com/sgl-project/ome](https://github.com/sgl-project/ome)
-- **Documentation**: [docs.sglang.ai/ome](https://docs.sglang.ai/ome/)
-- **Community**: Join our [Slack](https://slack.sglang.ai/) for support and discussions
+- **Documentation**: [docs.sglang.io/ome](https://docs.sglang.io/ome/)
+- **Community**: Join our [Slack](https://slack.sglang.io/) for support and discussions
 - **Contribute**: We welcome contributions from the community
 
 ## Acknowledgments
diff --git a/blog/2025-07-16-nvila.md b/blog/2025-07-16-nvila.md
@@ -411,6 +411,6 @@ We thank all contributors for their efforts in developing and integrating NVILA
 **Further Reading:**
 
 - [SGLang on GitHub](https://github.com/sgl-project/sglang)
-- [How to Support New Models in SGLang](https://docs.sglang.ai/supported_models/support_new_models.html)
+- [How to Support New Models in SGLang](https://docs.sglang.io/supported_models/support_new_models.html)
 - [SGLang PR for NVILA integration](https://github.com/sgl-project/sglang/pull/6106)
 - [SGLang PR for multimodal processors](https://github.com/sgl-project/sglang/pull/7629)
diff --git a/blog/2025-07-20-k2-large-scale-ep.md b/blog/2025-07-20-k2-large-scale-ep.md
@@ -84,7 +84,7 @@ helm upgrade --install ome-crd oci://ghcr.io/moirai-internal/charts/ome-crd --na
 helm upgrade --install ome oci://ghcr.io/moirai-internal/charts/ome-resources --namespace ome
 ```
 
-For detailed setup instructions, refer to the official [OME installation guide](https://docs.sglang.ai/ome/docs/installation/).
+For detailed setup instructions, refer to the official [OME installation guide](https://docs.sglang.io/ome/docs/installation/).
 
 **Registering the Kimi K2 Model**
 To enable OME to manage the Kimi K2 model family, apply the following ClusterBaseModel resource:
diff --git a/blog/2025-07-31-glm4-5.md b/blog/2025-07-31-glm4-5.md
@@ -97,4 +97,4 @@ Together, **GLM-4.5** and **SGLang** form a robust foundation for next-generatio
 We would like to express our heartfelt gratitude to the following teams and collaborators in this [PR](https://github.com/sgl-project/sglang/pull/8224):
 
 - **[GLM Team](https://github.com/THUDM/GLM)**: Yuxuan Zhang, Chenhui Zhang, Xin Lv, Zilin Zhu and colleagues.
-- **[SGLang Team and community](https://docs.sglang.ai/index.html)**: Biao He, Lifu Huang, Binyao Jiang, Minglei Zhu, Cheng Wan, Chang Su, Xinyuan Tong and many others.
+- **[SGLang Team and community](https://docs.sglang.io/index.html)**: Biao He, Lifu Huang, Binyao Jiang, Minglei Zhu, Cheng Wan, Chang Su, Xinyuan Tong and many others.
diff --git a/blog/2025-08-27-gpt-oss.md b/blog/2025-08-27-gpt-oss.md
@@ -102,7 +102,7 @@ which achieves:
 
 ## Powering Agentic Applications 🤖
 
-To better enable agentic workflows, SGLang offers [OpenAI Response API support](https://docs.sglang.ai/basic_usage/gpt_oss.html#responses-api) and [native chat completion support](https://docs.sglang.ai/advanced_features/tool_parser.html). Here is an example of how to build a simple web search agent with SGLang (`python3.12` and `gpt-oss` package are required for built-in tools, more setup details can be found [here](https://docs.sglang.ai/basic_usage/gpt_oss.html#responses-api)).
+To better enable agentic workflows, SGLang offers [OpenAI Response API support](https://docs.sglang.io/basic_usage/gpt_oss.html#responses-api) and [native chat completion support](https://docs.sglang.io/advanced_features/tool_parser.html). Here is an example of how to build a simple web search agent with SGLang (`python3.12` and `gpt-oss` package are required for built-in tools, more setup details can be found [here](https://docs.sglang.io/basic_usage/gpt_oss.html#responses-api)).
 
 Launch the server:
 
diff --git a/blog/2025-09-10-sglang-hicache.md b/blog/2025-09-10-sglang-hicache.md
@@ -55,7 +55,7 @@ This design has already enabled us to integrate three performant backends—[Moo
 
 ## **Benchmark**
 
-Try experience the performance gain on your own! You can find various benchmark about HiCache [here](https://github.com/sgl-project/sglang/tree/main/benchmark/hicache). Following we highlight two benchmark results using the provided benchmark scripts and you can find the config instructions of backends [here](https://github.com/sgl-project/sglang/tree/main/python/sglang/srt/mem_cache/storage). If you have any questions about benchmarking or deployment, feel free to open an issue on GitHub or post in our [slack channel](https://slack.sglang.ai/).
+Try experience the performance gain on your own! You can find various benchmark about HiCache [here](https://github.com/sgl-project/sglang/tree/main/benchmark/hicache). Following we highlight two benchmark results using the provided benchmark scripts and you can find the config instructions of backends [here](https://github.com/sgl-project/sglang/tree/main/python/sglang/srt/mem_cache/storage). If you have any questions about benchmarking or deployment, feel free to open an issue on GitHub or post in our [slack channel](https://slack.sglang.io/).
 
 ![3fs_benchmark.png](/images/blog/hicache/3fs_benchmark.png)
 
diff --git a/blog/2025-09-22-sglang-deterministic.md b/blog/2025-09-22-sglang-deterministic.md
@@ -26,7 +26,7 @@ Now let's dive into the some technical details.
 
 ## Why Deterministic Inference Matters
 
-The ability to achieve consistent outputs from large language models (LLMs) inference is increasingly important. For example, the indeterminism of inference results can implicitly transform on-policy reinforcement learning (RL) into off-policy RL as [researchers pointed out](https://fengyao.notion.site/off-policy-rl). However, even if we turn the temperature down to 0 in SGLang, the sampling is still not deterministic due to the use of dynamic batching and radix cache (past discussions [here](https://docs.sglang.ai/references/faq.html#the-results-are-not-deterministic-even-with-a-temperature-of-0)) .
+The ability to achieve consistent outputs from large language models (LLMs) inference is increasingly important. For example, the indeterminism of inference results can implicitly transform on-policy reinforcement learning (RL) into off-policy RL as [researchers pointed out](https://fengyao.notion.site/off-policy-rl). However, even if we turn the temperature down to 0 in SGLang, the sampling is still not deterministic due to the use of dynamic batching and radix cache (past discussions [here](https://docs.sglang.io/references/faq.html#the-results-are-not-deterministic-even-with-a-temperature-of-0)) .
 
 As mentioned in the [blog](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/), the largest source of nondeterminism is the varying batch sizes: Even when a user repeatedly submits the same prompt, the output can vary across runs, since the request may be batched together with other users' requests, and differences in batch size can lead to nondeterministic inference results.
 
diff --git a/blog/2025-10-22-KTransformers.md b/blog/2025-10-22-KTransformers.md
@@ -72,7 +72,7 @@ Before installation, ensure your system meets the following requirements:
 
 ### Step 1: Install SGLang
 
-Follow the official [SGLang installation guide](https://docs.sglang.ai/get_started/install.html) to install SGLang:
+Follow the official [SGLang installation guide](https://docs.sglang.io/get_started/install.html) to install SGLang:
 
 ```bash
 pip install "sglang[all]"
diff --git a/blog/2025-11-07-sglang-diffusion.md b/blog/2025-11-07-sglang-diffusion.md
@@ -225,5 +225,5 @@ Special thanks to NVIDIA and Voltage Park for their compute support.
 ## Learn more
 
 - Roadmap: [Diffusion (2025 Q4)](https://github.com/sgl-project/sglang/issues/12799)
-- Slack channel: [#diffusion](https://sgl-fru7574.slack.com/archives/C09P0HTKE6A) (join via slack.sglang.ai)
+- Slack channel: [#diffusion](https://sgl-fru7574.slack.com/archives/C09P0HTKE6A) (join via slack.sglang.io)
 
diff --git a/content/about.md b/content/about.md
@@ -97,5 +97,5 @@ These projects feature open models with millions of downloads, crowdsourced plat
 
 ## Contact us
 - Email us at [lmsys.org@gmail.com](mailto:lmsys.org@gmail.com).
-- Join us on [Slack](https://slack.sglang.ai).
+- Join us on [Slack](https://slack.sglang.io).
 - Follow us on [X](https://twitter.com/lmsysorg).
diff --git a/src/components/Nav.js b/src/components/Nav.js
@@ -42,7 +42,7 @@ export default function Nav() {
         <FaEnvelope />
         </a>
         <a
-          href="https://slack.sglang.ai"
+          href="https://slack.sglang.io"
           target="_blank"
           rel="noopener noreferrer"
         >
