From e169492543d575d2db56f1ac3c145242045f716e Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 26 Feb 2026 23:08:24 +0000 Subject: [PATCH] fix: this backend is CUDA only Signed-off-by: Ettore Di Giacinto --- .github/workflows/backend.yml | 42 --------------- .github/workflows/test-extra.yml | 19 ------- backend/index.yaml | 54 ++----------------- .../faster-qwen3-tts/requirements-cpu.txt | 4 -- .../faster-qwen3-tts/requirements-hipblas.txt | 4 -- .../faster-qwen3-tts/requirements-intel.txt | 4 -- .../faster-qwen3-tts/requirements-mps.txt | 3 -- 7 files changed, 4 insertions(+), 126 deletions(-) delete mode 100644 backend/python/faster-qwen3-tts/requirements-cpu.txt delete mode 100644 backend/python/faster-qwen3-tts/requirements-hipblas.txt delete mode 100644 backend/python/faster-qwen3-tts/requirements-intel.txt delete mode 100644 backend/python/faster-qwen3-tts/requirements-mps.txt diff --git a/.github/workflows/backend.yml b/.github/workflows/backend.yml index c33d69f72..b9f9da409 100644 --- a/.github/workflows/backend.yml +++ b/.github/workflows/backend.yml @@ -1149,19 +1149,6 @@ jobs: dockerfile: "./backend/Dockerfile.python" context: "./" ubuntu-version: '2404' - - build-type: 'hipblas' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-faster-qwen3-tts' - runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-24.04:6.4.4" - skip-drivers: 'false' - backend: "faster-qwen3-tts" - dockerfile: "./backend/Dockerfile.python" - context: "./" - ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -1515,19 +1502,6 @@ jobs: dockerfile: "./backend/Dockerfile.python" context: "./" ubuntu-version: '2404' - - build-type: 'intel' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-faster-qwen3-tts' - runs-on: 'arc-runner-set' - base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04" - skip-drivers: 'false' - backend: "faster-qwen3-tts" - dockerfile: "./backend/Dockerfile.python" - context: "./" - ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -1980,19 +1954,6 @@ jobs: dockerfile: "./backend/Dockerfile.python" context: "./" ubuntu-version: '2404' - - build-type: '' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-cpu-faster-qwen3-tts' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:24.04" - skip-drivers: 'false' - backend: "faster-qwen3-tts" - dockerfile: "./backend/Dockerfile.python" - context: "./" - ubuntu-version: '2404' - build-type: '' cuda-major-version: "" cuda-minor-version: "" @@ -2079,9 +2040,6 @@ jobs: - backend: "qwen-tts" tag-suffix: "-metal-darwin-arm64-qwen-tts" build-type: "mps" - - backend: "faster-qwen3-tts" - tag-suffix: "-metal-darwin-arm64-faster-qwen3-tts" - build-type: "mps" - backend: "voxcpm" tag-suffix: "-metal-darwin-arm64-voxcpm" build-type: "mps" diff --git a/.github/workflows/test-extra.yml b/.github/workflows/test-extra.yml index c3cb8abcc..fee41fe7f 100644 --- a/.github/workflows/test-extra.yml +++ b/.github/workflows/test-extra.yml @@ -304,25 +304,6 @@ jobs: run: | make --jobs=5 --output-sync=target -C backend/python/qwen-tts make --jobs=5 --output-sync=target -C backend/python/qwen-tts test - tests-faster-qwen3-tts: - runs-on: ubuntu-latest - steps: - - name: Clone - uses: actions/checkout@v6 - with: - submodules: true - - name: Dependencies - run: | - sudo apt-get update - sudo apt-get install -y build-essential ffmpeg - sudo apt-get install -y ca-certificates cmake curl patch python3-pip - # Install UV - curl -LsSf https://astral.sh/uv/install.sh | sh - pip install --user --no-cache-dir grpcio-tools==1.64.1 - - name: Test faster-qwen3-tts - run: | - make --jobs=5 --output-sync=target -C backend/python/faster-qwen3-tts - make --jobs=5 --output-sync=target -C backend/python/faster-qwen3-tts test tests-qwen-asr: runs-on: ubuntu-latest steps: diff --git a/backend/index.yaml b/backend/index.yaml index 1ed53165f..e518170ca 100644 --- a/backend/index.yaml +++ b/backend/index.yaml @@ -543,13 +543,10 @@ alias: "faster-qwen3-tts" capabilities: nvidia: "cuda12-faster-qwen3-tts" - intel: "intel-faster-qwen3-tts" - amd: "rocm-faster-qwen3-tts" - nvidia-l4t: "nvidia-l4t-faster-qwen3-tts" - metal: "metal-faster-qwen3-tts" - default: "cpu-faster-qwen3-tts" + default: "cuda12-faster-qwen3-tts" nvidia-cuda-13: "cuda13-faster-qwen3-tts" nvidia-cuda-12: "cuda12-faster-qwen3-tts" + nvidia-l4t: "nvidia-l4t-faster-qwen3-tts" nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts" nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts" icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png @@ -2309,25 +2306,12 @@ name: "faster-qwen3-tts-development" capabilities: nvidia: "cuda12-faster-qwen3-tts-development" - intel: "intel-faster-qwen3-tts-development" - amd: "rocm-faster-qwen3-tts-development" - nvidia-l4t: "nvidia-l4t-faster-qwen3-tts-development" - metal: "metal-faster-qwen3-tts-development" - default: "cpu-faster-qwen3-tts-development" + default: "cuda12-faster-qwen3-tts-development" nvidia-cuda-13: "cuda13-faster-qwen3-tts-development" nvidia-cuda-12: "cuda12-faster-qwen3-tts-development" + nvidia-l4t: "nvidia-l4t-faster-qwen3-tts-development" nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts-development" nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development" -- !!merge <<: *faster-qwen3-tts - name: "cpu-faster-qwen3-tts" - uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-faster-qwen3-tts" - mirrors: - - localai/localai-backends:latest-cpu-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "cpu-faster-qwen3-tts-development" - uri: "quay.io/go-skynet/local-ai-backends:master-cpu-faster-qwen3-tts" - mirrors: - - localai/localai-backends:master-cpu-faster-qwen3-tts - !!merge <<: *faster-qwen3-tts name: "cuda12-faster-qwen3-tts" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-faster-qwen3-tts" @@ -2348,26 +2332,6 @@ uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts" mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "intel-faster-qwen3-tts" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-faster-qwen3-tts" - mirrors: - - localai/localai-backends:latest-gpu-intel-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "intel-faster-qwen3-tts-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-faster-qwen3-tts" - mirrors: - - localai/localai-backends:master-gpu-intel-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "rocm-faster-qwen3-tts" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-faster-qwen3-tts" - mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "rocm-faster-qwen3-tts-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-qwen3-tts" - mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-faster-qwen3-tts - !!merge <<: *faster-qwen3-tts name: "nvidia-l4t-faster-qwen3-tts" uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-faster-qwen3-tts" @@ -2388,16 +2352,6 @@ uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts" mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "metal-faster-qwen3-tts" - uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-faster-qwen3-tts" - mirrors: - - localai/localai-backends:latest-metal-darwin-arm64-faster-qwen3-tts -- !!merge <<: *faster-qwen3-tts - name: "metal-faster-qwen3-tts-development" - uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-faster-qwen3-tts" - mirrors: - - localai/localai-backends:master-metal-darwin-arm64-faster-qwen3-tts ## qwen-asr - !!merge <<: *qwen-asr name: "qwen-asr-development" diff --git a/backend/python/faster-qwen3-tts/requirements-cpu.txt b/backend/python/faster-qwen3-tts/requirements-cpu.txt deleted file mode 100644 index cef3137a1..000000000 --- a/backend/python/faster-qwen3-tts/requirements-cpu.txt +++ /dev/null @@ -1,4 +0,0 @@ ---extra-index-url https://download.pytorch.org/whl/cpu -torch -torchaudio -faster-qwen3-tts diff --git a/backend/python/faster-qwen3-tts/requirements-hipblas.txt b/backend/python/faster-qwen3-tts/requirements-hipblas.txt deleted file mode 100644 index 10524cf84..000000000 --- a/backend/python/faster-qwen3-tts/requirements-hipblas.txt +++ /dev/null @@ -1,4 +0,0 @@ ---extra-index-url https://download.pytorch.org/whl/rocm6.3 -torch==2.7.1+rocm6.3 -torchaudio==2.7.1+rocm6.3 -faster-qwen3-tts diff --git a/backend/python/faster-qwen3-tts/requirements-intel.txt b/backend/python/faster-qwen3-tts/requirements-intel.txt deleted file mode 100644 index d6f3433bf..000000000 --- a/backend/python/faster-qwen3-tts/requirements-intel.txt +++ /dev/null @@ -1,4 +0,0 @@ ---extra-index-url https://download.pytorch.org/whl/xpu -torch -torchaudio -faster-qwen3-tts diff --git a/backend/python/faster-qwen3-tts/requirements-mps.txt b/backend/python/faster-qwen3-tts/requirements-mps.txt deleted file mode 100644 index 21b7a4eab..000000000 --- a/backend/python/faster-qwen3-tts/requirements-mps.txt +++ /dev/null @@ -1,3 +0,0 @@ -torch -torchaudio -faster-qwen3-tts