diff --git a/docs/platforms/cpu_server.md b/docs/platforms/cpu_server.md index 7da14ba44..9e9e407ce 100644 --- a/docs/platforms/cpu_server.md +++ b/docs/platforms/cpu_server.md @@ -81,6 +81,8 @@ git clone https://github.com/sgl-project/sglang.git cd sglang git checkout +# Use dedicated toml file +cp python/pyproject_other.toml python/pyproject.toml # Install SGLang dependent libs, and build SGLang main package pip install --upgrade pip setuptools conda install -y libsqlite==3.48.0 gperftools tbb libnuma numactl diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index 0272caba1..60d7f296a 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -2648,7 +2648,7 @@ class ServerArgs: # use bf16 for mxfp4 triton kernels self.dtype = "bfloat16" - elif "Llama4" in model_arch: + elif "Llama4" in model_arch and self.device != "cpu": assert self.attention_backend in { "fa3", "aiter",