From f810c44c6eb98fbfa78797ac00aa1373c59b1eb7 Mon Sep 17 00:00:00 2001 From: Michael Goin Date: Fri, 26 Sep 2025 13:13:35 -0600 Subject: [PATCH] Add CUDA arch 12.0 to installation guide There are several kernels available for 12.0, including quantized gemm --- docs/installation.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/installation.rst b/docs/installation.rst index d0c8b13b15..4040dd8ac3 100644 --- a/docs/installation.rst +++ b/docs/installation.rst @@ -80,7 +80,7 @@ You can follow the steps below to install FlashInfer from source code: .. code-block:: bash cd flashinfer - export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a" + export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0" python -m flashinfer.aot # Produces AOT kernels in aot-ops/ python -m pip install --no-build-isolation --verbose . @@ -109,7 +109,7 @@ You can follow the steps below to install FlashInfer from source code: .. code-block:: bash cd flashinfer - export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a" + export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0" python -m flashinfer.aot # Produces AOT kernels in aot-ops/ python -m build --no-isolation --wheel ls -la dist/