Installation Verification

Check whether SGLang is successfully installed.

python3 - <<'PY'
import sglang
import sgl_kernel
import torch

print("sglang_version=" + getattr(sglang, "__version__", "unknown"))
print("sgl_kernel_import=ok") 
print("torch_cuda=" + str(torch.version.cuda)) 
print("cuda_built=" + str(torch.backends.cuda.is_built())) 
print("cuda_available=" + str(torch.cuda.is_available())) 
assert getattr(sglang, "__version__", "") == "0.5.10"
assert torch.backends.cuda.is_built() 
assert torch.cuda.is_available() 
PY

The expected output is as follows.

sglang_version=0.5.10 
sgl_kernel_import=ok 
torch_cuda=13.0 
cuda_built=True 
cuda_available=True

Launch the SGLang inference service as a minimal quick start example.
1 2 3 4
python3 -m sglang.launch_server \ --model-path facebook/opt-125m \ --host 0.0.0.0 \ --port 30000
After the service is started, run the following command to check whether the API is accessible.
1
curl http://127.0.0.1:30000/health
facebook/opt-125m is a small-scale public model, which is suitable for verifying that the service process and API can be started. Replace it with the actual service model in the production environment.

Parent topic: Installation Guide