feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang

.github/workflows/backend.yml

@@ -920,6 +920,32 @@ jobs:
             backend: "turboquant"
             dockerfile: "./backend/Dockerfile.turboquant"
             context: "./"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-vllm'
+            runs-on: 'arc-runner-set'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "vllm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-vllm-omni'
+            runs-on: 'arc-runner-set'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "vllm-omni"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -1076,6 +1102,45 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-vllm'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "vllm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-vllm-omni'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "vllm-omni"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-sglang'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "sglang"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
           - build-type: 'l4t'
             cuda-major-version: "13"
             cuda-minor-version: "0"

backend/index.yaml

@@ -161,7 +161,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr"
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
     metal: "metal-rfdetr"
     default: "cpu-rfdetr"
@@ -263,6 +263,8 @@
     amd: "rocm-vllm"
     intel: "intel-vllm"
     nvidia-cuda-12: "cuda12-vllm"
+    nvidia-cuda-13: "cuda13-vllm"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vllm"
     cpu: "cpu-vllm"
 - &sglang
   name: "sglang"
@@ -285,6 +287,7 @@
     amd: "rocm-sglang"
     intel: "intel-sglang"
     nvidia-cuda-12: "cuda12-sglang"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-sglang"
     cpu: "cpu-sglang"
 - &vllm-omni
   name: "vllm-omni"
@@ -311,6 +314,8 @@
     nvidia: "cuda12-vllm-omni"
     amd: "rocm-vllm-omni"
     nvidia-cuda-12: "cuda12-vllm-omni"
+    nvidia-cuda-13: "cuda13-vllm-omni"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vllm-omni"
 - &mlx
   name: "mlx"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx"
@@ -1814,12 +1819,25 @@
     nvidia: "cuda12-vllm-development"
     amd: "rocm-vllm-development"
     intel: "intel-vllm-development"
+    nvidia-cuda-12: "cuda12-vllm-development"
+    nvidia-cuda-13: "cuda13-vllm-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vllm-development"
     cpu: "cpu-vllm-development"
 - !!merge <<: *vllm
   name: "cuda12-vllm"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm"
   mirrors:
     - localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm
+- !!merge <<: *vllm
+  name: "cuda13-vllm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vllm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-vllm
+- !!merge <<: *vllm
+  name: "cuda13-nvidia-l4t-arm64-vllm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm
 - !!merge <<: *vllm
   name: "rocm-vllm"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm"
@@ -1840,6 +1858,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-vllm
+- !!merge <<: *vllm
+  name: "cuda13-vllm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vllm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-vllm
+- !!merge <<: *vllm
+  name: "cuda13-nvidia-l4t-arm64-vllm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vllm"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vllm
 - !!merge <<: *vllm
   name: "rocm-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm"
@@ -1862,12 +1890,19 @@
     nvidia: "cuda12-sglang-development"
     amd: "rocm-sglang-development"
     intel: "intel-sglang-development"
+    nvidia-cuda-12: "cuda12-sglang-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-sglang-development"
     cpu: "cpu-sglang-development"
 - !!merge <<: *sglang
   name: "cuda12-sglang"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-sglang"
   mirrors:
     - localai/localai-backends:latest-gpu-nvidia-cuda-12-sglang
+- !!merge <<: *sglang
+  name: "cuda13-nvidia-l4t-arm64-sglang"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-sglang"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-sglang
 - !!merge <<: *sglang
   name: "rocm-sglang"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-sglang"
@@ -1888,6 +1923,11 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-sglang"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-sglang
+- !!merge <<: *sglang
+  name: "cuda13-nvidia-l4t-arm64-sglang-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-sglang"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-sglang
 - !!merge <<: *sglang
   name: "rocm-sglang-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-sglang"
@@ -1910,11 +1950,23 @@
     nvidia: "cuda12-vllm-omni-development"
     amd: "rocm-vllm-omni-development"
     nvidia-cuda-12: "cuda12-vllm-omni-development"
+    nvidia-cuda-13: "cuda13-vllm-omni-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vllm-omni-development"
 - !!merge <<: *vllm-omni
   name: "cuda12-vllm-omni"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm-omni"
   mirrors:
     - localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm-omni
+- !!merge <<: *vllm-omni
+  name: "cuda13-vllm-omni"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vllm-omni"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-vllm-omni
+- !!merge <<: *vllm-omni
+  name: "cuda13-nvidia-l4t-arm64-vllm-omni"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-omni"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-omni
 - !!merge <<: *vllm-omni
   name: "rocm-vllm-omni"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm-omni"
@@ -1925,6 +1977,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm-omni"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-vllm-omni
+- !!merge <<: *vllm-omni
+  name: "cuda13-vllm-omni-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vllm-omni"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-vllm-omni
+- !!merge <<: *vllm-omni
+  name: "cuda13-nvidia-l4t-arm64-vllm-omni-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-omni"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-omni
 - !!merge <<: *vllm-omni
   name: "rocm-vllm-omni-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm-omni"
@@ -1936,7 +1998,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr-development"
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
     metal: "metal-rfdetr-development"
     default: "cpu-rfdetr-development"

backend/python/sglang/install.sh

@@ -23,6 +23,19 @@ if [ "x${BUILD_PROFILE}" == "xcpu" ]; then
     EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
 fi
 
+# JetPack 7 / L4T arm64 wheels are built for cp312 and shipped via
+# pypi.jetson-ai-lab.io. Bump the venv Python so the prebuilt sglang
+# wheel resolves cleanly. unsafe-best-match is required because the
+# jetson-ai-lab index lists transitive deps (e.g. decord) at older
+# versions only — without it uv refuses to fall through to PyPI for a
+# compatible wheel and resolution fails.
+if [ "x${BUILD_PROFILE}" == "xl4t13" ]; then
+    PYTHON_VERSION="3.12"
+    PYTHON_PATCH="12"
+    PY_STANDALONE_TAG="20251120"
+    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
+fi
+
 # sglang's CPU path has no prebuilt wheel on PyPI — upstream publishes
 # a separate pyproject_cpu.toml that must be swapped in before `pip install`.
 # Reference: docker/xeon.Dockerfile in the sglang upstream repo.

backend/python/sglang/requirements-l4t13.txt

@@ -0,0 +1,12 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+accelerate
+torch
+torchvision
+torchaudio
+transformers
+# Drop the [all] extra: it pulls outlines/decord, and decord has no
+# aarch64 cp312 wheel anywhere (PyPI nor the jetson-ai-lab index ships
+# only legacy cp35-cp37). With [all] uv backtracks through versions
+# trying to satisfy decord and lands on sglang==0.1.16. Floor at 0.5.0
+# so uv can't silently downgrade if a future resolution misfires.
+sglang>=0.5.0

backend/python/vllm-omni/install.sh

@@ -12,11 +12,15 @@ else
     source $backend_dir/../common/libbackend.sh
 fi
 
-# Handle l4t build profiles (Python 3.12, pip fallback) if needed
+# Handle l4t build profiles (Python 3.12, pip fallback) if needed.
+# unsafe-best-match is required on l4t13 because the jetson-ai-lab index
+# lists transitive deps at limited versions — without it uv pins to the
+# first matching index and fails to resolve a compatible wheel from PyPI.
 if [ "x${BUILD_PROFILE}" == "xl4t13" ]; then
   PYTHON_VERSION="3.12"
   PYTHON_PATCH="12"
   PY_STANDALONE_TAG="20251120"
+  EXTRA_PIP_INSTALL_FLAGS="${EXTRA_PIP_INSTALL_FLAGS:-} --index-strategy=unsafe-best-match"
 fi
 
 if [ "x${BUILD_PROFILE}" == "xl4t12" ]; then
@@ -26,16 +30,38 @@ fi
 # Install base requirements first
 installRequirements
 
-# Install vllm based on build type
+# Install vllm based on build type. vllm-omni tracks vllm master from
+# source (cloned below) so we leave the upstream vllm dependency unpinned
+# — vllm 0.19+ ships cu130 wheels by default, which is what we want for
+# cublas13. Older cuda12/rocm/cpu paths still resolve a compatible wheel
+# from the relevant channel.
 if [ "x${BUILD_TYPE}" == "xhipblas" ]; then
     # ROCm
     if [ "x${USE_PIP}" == "xtrue" ]; then
         pip install vllm==0.14.0 --extra-index-url https://wheels.vllm.ai/rocm/0.14.0/rocm700
     else
         uv pip install vllm==0.14.0 --extra-index-url https://wheels.vllm.ai/rocm/0.14.0/rocm700
     fi
+elif [ "x${BUILD_PROFILE}" == "xl4t13" ]; then
+    # JetPack 7 / L4T arm64 cu130 — vllm comes from the prebuilt SBSA wheel
+    # at jetson-ai-lab. Version is unpinned: the index ships whatever build
+    # matches the cu130/cp312 ABI. unsafe-best-match lets uv fall through
+    # to PyPI for transitive deps not present on the jetson-ai-lab index.
+    if [ "x${USE_PIP}" == "xtrue" ]; then
+        pip install vllm --extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+    else
+        uv pip install --index-strategy=unsafe-best-match vllm --extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+    fi
+elif [ "x${BUILD_PROFILE}" == "xcublas13" ]; then
+    # vllm 0.19+ defaults to cu130 wheels on PyPI, no extra index needed.
+    if [ "x${USE_PIP}" == "xtrue" ]; then
+        pip install vllm --torch-backend=auto
+    else
+        uv pip install vllm --torch-backend=auto
+    fi
 elif [ "x${BUILD_TYPE}" == "xcublas" ] || [ "x${BUILD_TYPE}" == "x" ]; then
-    # CUDA (default) or CPU
+    # cuda12 / CPU — keep the 0.14.0 pin for compatibility with the existing
+    # cuda12 vllm-omni image; bumping should be its own change.
     if [ "x${USE_PIP}" == "xtrue" ]; then
         pip install vllm==0.14.0 --torch-backend=auto
     else

backend/python/vllm-omni/requirements-cublas13.txt

@@ -0,0 +1,5 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+accelerate
+torch
+transformers
+bitsandbytes

backend/python/vllm-omni/requirements-l4t13.txt

@@ -0,0 +1,13 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+accelerate
+torch
+torchvision
+torchaudio
+transformers
+bitsandbytes
+flash-attn
+diffusers
+librosa
+soundfile
+pillow
+numpy

backend/python/vllm/install.sh

@@ -32,6 +32,22 @@ if [ "x${BUILD_PROFILE}" == "xcpu" ]; then
     EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
 fi
 
+# JetPack 7 / L4T arm64 wheels (torch, vllm, flash-attn) live on
+# pypi.jetson-ai-lab.io and are built for cp312, so bump the venv Python
+# accordingly. JetPack 6 keeps cp310 + USE_PIP=true. unsafe-best-match
+# is required because the jetson-ai-lab index lists transitive deps at
+# limited versions — without it uv pins to the first matching index and
+# fails to resolve a compatible wheel from PyPI.
+if [ "x${BUILD_PROFILE}" == "xl4t12" ]; then
+    USE_PIP=true
+fi
+if [ "x${BUILD_PROFILE}" == "xl4t13" ]; then
+    PYTHON_VERSION="3.12"
+    PYTHON_PATCH="12"
+    PY_STANDALONE_TAG="20251120"
+    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
+fi
+
 # FROM_SOURCE=true on a CPU build skips the prebuilt vllm wheel in
 # requirements-cpu-after.txt and compiles vllm locally against the host's
 # actual CPU. Not used by default because it takes ~30-40 minutes, but

backend/python/vllm/requirements-cublas13-after.txt

@@ -0,0 +1,2 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+vllm

backend/python/vllm/requirements-cublas13.txt

@@ -0,0 +1,5 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+accelerate
+torch
+transformers
+bitsandbytes

backend/python/vllm/requirements-l4t13-after.txt

@@ -0,0 +1,2 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+vllm

backend/python/vllm/requirements-l4t13.txt

@@ -0,0 +1,8 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/sbsa/cu130
+accelerate
+torch
+torchvision
+torchaudio
+transformers
+bitsandbytes
+flash-attn