Run SGLang Thor & Spark Install uv curl -LsSf https://astral.sh/uv/install.sh | sh Create environment uv venv .sglang --python 3.12 source .sglang/bin/activate sudo apt install python3-dev python3.12-dev Export variables export TORCH_CUDA_ARCH_LIST=11.0a export TRITON_PTXAS_PATH=/usr/local/c…

Hello, thanks @johnny_nv , it was useful. Installation Steps for sgl-kernel on Jetson Thor 🚀 Install cmake ARCH=$(uname -m) wget ``https://cmake.org/files/v3.31/cmake-3.31.1-linux-${ARCH}.tar.gz tar -xzf cmake-3.31.1-linux-${ARCH}.tar.gz mv cmake-3.31.1-linux-${ARCH} /opt/cmake export PATH=/op…

[image] johnny_nv: whl/cu130/sgl-kernel/index.html at gh-pages · sgl-project/whl · GitHub I install sgl_kernel cu130 wheel, run command: ```python -m sglang.launch_server --model /root/zl/Qwen3-VL-8B-Instruct``` bug got error: from sgl_kernel import gelu_and_mul, silu_and_mul File "/…

did you installed from this? Release v0.3.16.post4 · sgl-project/whl · GitHub did you install pytorch 2.9.0 cu130? did you export correctly your export variables?

I use the NGC pytorch image 25.09 as base image, and install sglang from source. git clone --recursive https://github.com/sgl-project/sglang.git cd sglang pip install -e "python[cu130]" pip install sgl_kerne sgl_kernel-0.3.16.post4+cu130-cp310-abi3-manylinux2014_aarch64.whl export TORCH_CUDA_ARC…

25.10 was released: SGLang | NVIDIA NGC

I followed the installation steps of the initial post but when I run a model with the sglang.launch_server module, it terminates with: ”RuntimeError: No accelerator (CUDA, XPU, HPU) is available.”

I don’t know sglang but this might help. env |grep -i cuda If following values aren't returned, set them and add to ~/.bashrc CUDA_HOME=/usr/local/cuda LIBRARY_PATH=/usr/local/cuda-13.0/targets/sbsa-linux/lib PATH=$PATH:/usr/local/cuda/bin

I have the same problem. raise RuntimeError("No accelerator (CUDA, XPU, HPU) is available.") RuntimeError: No accelerator (CUDA, XPU, HPU) is available.

Did you install pytorch 2.9.1 cu130? Did you build it with that version?

I used the installation procedure exactly described in the initial post of this thread and the way it installs torch. The version that was installed this way is: 2.9.0+cu130

Run SGLang in Thor

Robotics & Edge Computing Jetson Systems Jetson Thor

johnny_nv October 26, 2025, 1:40am 3

SGLANG Released: cu130 kernels can be downloaded here
https://github.com/sgl-project/whl/blob/gh-pages/cu130/sgl-kernel/index.html

Topic		Replies	Views
Run SGLang in Spark DGX Spark / GB10	20	2615	November 28, 2025
Build SGLang from source on Blackwell Pro 6000/ DGX Spark DGX Spark / GB10 jetson , nemotron	14	983	March 4, 2026
[Help Needed] Building vLLM dependencies inside SGLang official image for Eagle-3 Speculative Decoding Jetson Thor llm	14	402	December 29, 2025
Setting up multiple instances of the SGLang server using router on the NVIDIA Jetson AGX Orin 64GB dev kit Jetson Projects	0	539	June 9, 2025
New pre-built sglang Docker Images for NVIDIA DGX Spark DGX Spark / GB10 Projects	27	2130	May 7, 2026
Error when use SGLang:26.03-py3 to deploy Qwen3.5-35B-A3B-FP8 DGX Spark / GB10	1	131	April 1, 2026
Sglang:26.02-py3 requires installation of 3 python modules Jetson Thor python , llm	4	94	April 11, 2026
Error When Validating Qwen3-32B-FP8 Performance Using sglang (Fp8LinearMethod AttributeError) DGX Spark / GB10 cuda	15	398	January 1, 2026
SOTA inference speed using SGlang and EAGLE-3 speculative decoding on the NVIDIA Jetson AGX Orin Jetson Projects llama-31-8b-instruct , llama	2	1121	March 23, 2025
Setting up vLLM, SGLang or TensorRT on two DGX Sparks DGX Spark / GB10	16	1876	December 7, 2025

Run SGLang in Thor

Related topics