From c2bd41ac9f64cd873afa8a061f14192adaadbf7e Mon Sep 17 00:00:00 2001
From: Huy Do <huydhn@gmail.com>
Date: Thu, 16 Oct 2025 01:03:26 +0000
Subject: [PATCH] Build vLLM nightly wheels for CUDA 13.0 (#163239)

Now that https://github.com/vllm-project/vllm/pull/24599 has been merged
Pull Request resolved: https://github.com/pytorch/pytorch/pull/163239
Approved by: https://github.com/malfet, https://github.com/atalman
---
 .../build-external-packages/action.yml        |  2 +-
 .github/workflows/build-vllm-wheel.yml        | 19 ++++++++++++++++---
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/.github/actions/build-external-packages/action.yml b/.github/actions/build-external-packages/action.yml
index c0c727d93ac6..049c3ce28e45 100644
--- a/.github/actions/build-external-packages/action.yml
+++ b/.github/actions/build-external-packages/action.yml
@@ -65,7 +65,7 @@ runs:
           cd .ci/lumen_cli
           python3 -m pip install -e .
         )
-        MAX_JOBS="$(nproc --ignore=6)"
+        MAX_JOBS="$(nproc --ignore=10)"
         export MAX_JOBS
 
         # Split the comma-separated list and build each target
diff --git a/.github/workflows/build-vllm-wheel.yml b/.github/workflows/build-vllm-wheel.yml
index 2c6635374841..4526faf6d7fc 100644
--- a/.github/workflows/build-vllm-wheel.yml
+++ b/.github/workflows/build-vllm-wheel.yml
@@ -27,9 +27,8 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [ '3.12' ]
-        # TODO (huydhn): Add cu130 after https://github.com/vllm-project/vllm/issues/24464 is resolved
         platform: [ 'manylinux_2_28_x86_64', 'manylinux_2_28_aarch64' ]
-        device: [ 'cu128', 'cu129' ]
+        device: [ 'cu128', 'cu129', 'cu130' ]
         include:
           - platform: manylinux_2_28_x86_64
             device: cu128
@@ -39,6 +38,10 @@ jobs:
             device: cu129
             manylinux-image: 'pytorch/manylinux2_28-builder:cuda12.9'
             runner: linux.12xlarge.memory
+          - platform: manylinux_2_28_x86_64
+            device: cu130
+            manylinux-image: 'pytorch/manylinux2_28-builder:cuda13.0'
+            runner: linux.12xlarge.memory
           - platform: manylinux_2_28_aarch64
             device: cu128
             manylinux-image: 'pytorch/manylinuxaarch64-builder:cuda12.8'
@@ -47,6 +50,11 @@ jobs:
             device: cu129
             manylinux-image: 'pytorch/manylinuxaarch64-builder:cuda12.9'
             runner: linux.arm64.r7g.12xlarge.memory
+        exclude:
+          # TODO (huydhn): Add cu130 aarch64 once PyTorch is on 2.9+ and
+          # xformers is update to support 13.0
+          - platform: manylinux_2_28_aarch64
+            device: cu130
     name: "Build ${{ matrix.device }} vLLM wheel on ${{ matrix.platform }}"
     runs-on: ${{ matrix.runner }}
     timeout-minutes: 480
@@ -169,7 +177,12 @@ jobs:
       fail-fast: false
       matrix:
         platform: [ 'manylinux_2_28_x86_64', 'manylinux_2_28_aarch64' ]
-        device: [ 'cu128', 'cu129' ]
+        device: [ 'cu128', 'cu129', 'cu130' ]
+        exclude:
+          # TODO (huydhn): Add cu130 aarch64 once PyTorch is on 2.9+ and
+          # xformers is update to support 13.0
+          - platform: manylinux_2_28_aarch64
+            device: cu130
     env:
       PLATFORM: ${{ matrix.platform }}
       BUILD_DEVICE: ${{ matrix.device }}