diff --git a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
index 6103ca0b7..b1bd86793 100644
--- a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
+++ b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
@@ -89,7 +89,7 @@ import { benchmarks } from "/src/snippets/configs/deepseek-ai/deepseek-v4-benchm
 <Deployment config={config} benchmarks={benchmarks} />
 
 <Note>
-  For a runnable end-to-end example, see the [DeepSeek-V4-Flash demo notebook](/demo/deepseek_v4_flash).
+  For a runnable end-to-end example, see the [DeepSeek-V4-Flash demo notebook](https://github.com/sgl-project/sglang/blob/main/docs_new/demo/deepseek_v4_flash.ipynb).
 </Note>
 
 <div style={{fontSize: "0.85em", lineHeight: "1.55", color: "#6b7280", margin: "0.5rem 0 1rem 0"}}>
diff --git a/docs_new/cookbook/autoregressive/GLM/GLM-4.7.mdx b/docs_new/cookbook/autoregressive/GLM/GLM-4.7.mdx
index ff30024e4..846dc551a 100644
--- a/docs_new/cookbook/autoregressive/GLM/GLM-4.7.mdx
+++ b/docs_new/cookbook/autoregressive/GLM/GLM-4.7.mdx
@@ -127,7 +127,7 @@ Pick a weight format by hardware: **NVFP4** on NVIDIA Blackwell (B200, GB200), *
 - **EAGLE Speculative Decoding:** Supported for GLM-4.7. Add `--speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4`. The spec-v2 overlap scheduler is enabled by default; pass `--disable-overlap-schedule` to disable. Enable via the interactive command generator above.
 - **Thinking Budget:** Use `--enable-custom-logit-processor` flag and pass `Glm4MoeThinkingBudgetLogitProcessor` in requests to cap the model's thinking token count (see section 4.2.3).
 
-For general GLM-4.x family launch guidance (AMD ROCm notes and more), see [Launch GLM-4.5 / GLM-4.6 / GLM-4.7 with SGLang](../../../docs/basic_usage/glm45). Per-hardware bench commands and flags are inline in §5.1 below.
+For general GLM-4.x family launch guidance (AMD ROCm notes and more), see [Launch GLM-4.5 / GLM-4.6 / GLM-4.7 with SGLang](/cookbook/autoregressive/GLM/GLM-4.5). Per-hardware bench commands and flags are inline in §5.1 below.
 
 ## 4. Model Invocation
 
diff --git a/docs_new/cookbook/autoregressive/NVIDIA/Nemotron3-Nano-Omni.mdx b/docs_new/cookbook/autoregressive/NVIDIA/Nemotron3-Nano-Omni.mdx
index 6bfde97fe..bfa029df9 100644
--- a/docs_new/cookbook/autoregressive/NVIDIA/Nemotron3-Nano-Omni.mdx
+++ b/docs_new/cookbook/autoregressive/NVIDIA/Nemotron3-Nano-Omni.mdx
@@ -52,7 +52,7 @@ uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=pytho
 docker pull lmsysorg/sglang:dev-cu13-nemotronh-nano-omni-reasoning-v3
 ```
 
-For the full Docker setup and other installation methods, refer to the [official SGLang installation guide](../../../docs/get-started/installation).
+For the full Docker setup and other installation methods, refer to the [official SGLang installation guide](../../../docs/get-started/install).
 
 ## 3. Model Deployment