[chore] release fastvideo-kernel 0.3.0 (#1478)

Author: SolitaryThinker

.github/workflows/publish-kernel.yml

@@ -53,23 +53,15 @@ jobs:
       fail-fast: false
       matrix:
           os: [ubuntu-22.04]
-          python-version: ['3.10', '3.11', '3.12']
+          python-version: ['3.12']
           torch-cuda:
-            # - torch-version: '2.5.1'
-            #   cuda-version: '12.4.1'
-            #   torch-cuda-short: 'cu124'
-            # - torch-version: '2.6.0'
-            #   cuda-version: '12.6.3'
-            #   torch-cuda-short: 'cu126'
-            # - torch-version: '2.7.1'
-            #   cuda-version: '12.8.0'
-            #   torch-cuda-short: 'cu128'
-            # - torch-version: '2.9.1'
-            #   cuda-version: '12.8.0'
-            #   torch-cuda-short: 'cu128'
-            - torch-version: '2.10.0'
-              cuda-version: '12.8.0'
-              torch-cuda-short: 'cu128'
+            # torch 2.12 dropped cu128; cu130 (CUDA 13) is the default wheel, cu126 covers older drivers.
+            - torch-version: '2.12.0'
+              cuda-version: '12.6.3'
+              torch-cuda-short: 'cu126'
+            - torch-version: '2.12.0'
+              cuda-version: '13.0.0'
+              torch-cuda-short: 'cu130'
 
     steps:
       - name: Free up disk space
@@ -152,9 +144,17 @@ jobs:
 
           cd fastvideo-kernel
           git submodule update --init --recursive  # Ensure ThunderKittens submodule is initialized
-          # Release builds are produced on GPU-less runners, so force-enable TK and target Hopper.
-          export TORCH_CUDA_ARCH_LIST="9.0a"
-          export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+          # Release builds run on GPU-less runners, so force-enable TK and set the arch explicitly.
+          # The CUDA 13 (cu130) leg additionally targets Blackwell sm_120a and builds the
+          # attn_qat_infer FP4 inference kernels (they need CUDA Toolkit 12.8+, so the cu126 leg
+          # stays Hopper-only and ships without them).
+          if [ "${{ matrix.torch-cuda.torch-cuda-short }}" = "cu130" ]; then
+            export TORCH_CUDA_ARCH_LIST="9.0a;12.0a"
+            export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DFASTVIDEO_KERNEL_BUILD_ATTN_QAT_INFER=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+          else
+            export TORCH_CUDA_ARCH_LIST="9.0a"
+            export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+          fi
 
           # Build standard wheel (no local version suffix) for PyPI
           python -m build --wheel --outdir dist
@@ -183,8 +183,8 @@ jobs:
           mv fixed_dist/*.whl dist/
 
       - name: Upload wheel artifact
-        # Only upload if it's the "main" CUDA version we want on PyPI
-        # We upload all to artifacts for inspection/GH releases, but give them distinct artifact names
+        # Upload every matrix leg as a distinct artifact (for inspection / GitHub releases).
+        # The publish job below selects which CUDA build is pushed to PyPI.
         uses: actions/upload-artifact@v4
         with:
           name: fastvideo_kernel-py${{ matrix.python-version }}-${{ matrix.torch-cuda.torch-cuda-short }}-torch${{ matrix.torch-cuda.torch-version }}
@@ -204,13 +204,15 @@ jobs:
 
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Download PyPI wheels
+        # Publish only the cu130 (CUDA 13) wheel to PyPI — it includes the Blackwell FP4 kernels.
+        # The cu126 wheel stays available as a build artifact / GitHub-release asset.
         uses: actions/download-artifact@v4
         with:
           path: fastvideo-kernel/dist/
-          pattern: 'fastvideo_kernel-py*'
+          pattern: 'fastvideo_kernel-py*-cu130-*'
           merge-multiple: true
 
       - name: Install uv

apps/dreamverse/docker/README.md

@@ -32,7 +32,7 @@ checkout with the `dreamverse` extra, installs the FA4
 flash-attention fork, builds native FFmpeg, and installs FlashInfer for NVFP4
 quantization.
 
-FastVideo's pinned `fastvideo-kernel==0.2.6` package is installed by default.
+FastVideo's pinned `fastvideo-kernel==0.3.0` package is installed by default.
 To rebuild `fastvideo-kernel` from this checkout during the image build, set:
 
 ```bash

fastvideo-kernel/pyproject.toml

@@ -9,7 +9,7 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "fastvideo-kernel"
-version = "0.2.6"
+version = "0.3.0"
 description = "Unified CUDA kernels for FastVideo"
 readme = "README.md"
 requires-python = ">=3.10"

fastvideo-kernel/python/fastvideo_kernel/version.py

@@ -1 +1 @@
-__version__ = "0.2.6"
+__version__ = "0.3.0"

pyproject.toml

@@ -67,7 +67,7 @@ dependencies = [
     "remote-pdb",
 
     # Kernel & Packaging
-    "fastvideo-kernel==0.2.6",
+    "fastvideo-kernel==0.3.0",
     "wheel",
 
     # Training Dependencies

pyproject_other.toml

@@ -65,7 +65,7 @@ dependencies = [
     "remote-pdb",
 
     # Kernel & Packaging
-    "fastvideo-kernel==0.2.6",
+    "fastvideo-kernel==0.3.0",
     "wheel",
 
     # Training Dependencies