From 94fc26aad8bdbc9eb73c68ab883a1a36a195c7a6 Mon Sep 17 00:00:00 2001 From: Baizhou Zhang Date: Sat, 10 Jan 2026 14:03:19 +0800 Subject: [PATCH] [Doc]Update note for Cuda 13 container usage (#16805) --- docs/get_started/install.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/get_started/install.md b/docs/get_started/install.md index a2329124a..509a34248 100644 --- a/docs/get_started/install.md +++ b/docs/get_started/install.md @@ -204,3 +204,4 @@ echo "Build and push completed successfully!" - [FlashInfer](https://github.com/flashinfer-ai/flashinfer) is the default attention kernel backend. It only supports sm75 and above. If you encounter any FlashInfer-related issues on sm75+ devices (e.g., T4, A10, A100, L4, L40S, H100), please switch to other kernels by adding `--attention-backend triton --sampling-backend pytorch` and open an issue on GitHub. - To reinstall flashinfer locally, use the following command: `pip3 install --upgrade flashinfer-python --force-reinstall --no-deps` and then delete the cache with `rm -rf ~/.cache/flashinfer`. +- To run sglang in Cuda 13 environment, please use the following docker: `docker pull lmsysorg/sglang:latest-cu130-runtime`.