From 7bef11706fbc51529538ef3b3fda8610b1c29235 Mon Sep 17 00:00:00 2001 From: Zihao Ye Date: Thu, 13 Nov 2025 22:35:00 -0500 Subject: [PATCH] upd --- .github/workflows/nightly-release.yml | 2 +- .github/workflows/release.yml | 2 +- README.md | 2 +- docs/installation.rst | 2 +- scripts/task_test_jit_cache_package_build_import.sh | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/workflows/nightly-release.yml b/.github/workflows/nightly-release.yml index 2e7230cfa5..7c57d4bd7a 100644 --- a/.github/workflows/nightly-release.yml +++ b/.github/workflows/nightly-release.yml @@ -145,7 +145,7 @@ jobs: - name: Build wheel in container env: DOCKER_IMAGE: ${{ matrix.arch == 'aarch64' && format('pytorch/manylinuxaarch64-builder:cuda{0}', matrix.cuda) || format('pytorch/manylinux2_28-builder:cuda{0}', matrix.cuda) }} - FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0f 12.0f' }} + FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f' }} FLASHINFER_DEV_RELEASE_SUFFIX: ${{ needs.setup.outputs.dev_suffix }} run: | # Extract CUDA major and minor versions diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 0c95611c50..b11e72e1f7 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -182,7 +182,7 @@ jobs: - name: Build wheel in container env: DOCKER_IMAGE: ${{ matrix.arch == 'aarch64' && format('pytorch/manylinuxaarch64-builder:cuda{0}', matrix.cuda) || format('pytorch/manylinux2_28-builder:cuda{0}', matrix.cuda) }} - FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0f 12.0f' }} + FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f' }} run: | # Extract CUDA major and minor versions CUDA_MAJOR=$(echo "${{ matrix.cuda }}" | cut -d'.' -f1) diff --git a/README.md b/README.md index 88b579b180..81b8583242 100644 --- a/README.md +++ b/README.md @@ -90,7 +90,7 @@ python -m pip install dist/*.whl `flashinfer-jit-cache` (customize `FLASHINFER_CUDA_ARCH_LIST` for your target GPUs): ```bash -export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 10.0a 10.3a 11.0f 12.0f" +export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 10.0a 10.3a 11.0a 12.0f" cd flashinfer-jit-cache python -m build --no-isolation --wheel python -m pip install dist/*.whl diff --git a/docs/installation.rst b/docs/installation.rst index 9087e87471..eb2f1acf67 100644 --- a/docs/installation.rst +++ b/docs/installation.rst @@ -92,7 +92,7 @@ You can follow the steps below to install FlashInfer from source code: .. code-block:: bash - export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 10.0a 10.3a 11.0f 12.0f" + export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 10.0a 10.3a 11.0a 12.0f" cd flashinfer-jit-cache python -m build --no-isolation --wheel python -m pip install dist/*.whl diff --git a/scripts/task_test_jit_cache_package_build_import.sh b/scripts/task_test_jit_cache_package_build_import.sh index d03937bc47..0627d7b82d 100755 --- a/scripts/task_test_jit_cache_package_build_import.sh +++ b/scripts/task_test_jit_cache_package_build_import.sh @@ -46,7 +46,7 @@ if cuda_ver is not None: if (major, minor) >= (13, 0): arches.append("10.0a") arches.append("10.3a") - arches.append("11.0f") + arches.append("11.0a") arches.append("12.0f") elif (major, minor) >= (12, 9): arches.append("10.0a")