diff --git a/.github/workflows/backend.yml b/.github/workflows/backend.yml index a18068c754f5..c6ec48315d27 100644 --- a/.github/workflows/backend.yml +++ b/.github/workflows/backend.yml @@ -39,62 +39,9 @@ jobs: #max-parallel: ${{ github.event_name != 'pull_request' && 6 || 4 }} matrix: include: - # CUDA 11 builds - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-rerankers' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "rerankers" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-llama-cpp' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "llama-cpp" - dockerfile: "./backend/Dockerfile.llama-cpp" - context: "./" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-transformers' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "transformers" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-diffusers' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "diffusers" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - build-type: 'l4t' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/arm64' tag-latest: 'auto' tag-suffix: '-nvidia-l4t-diffusers' @@ -103,8 +50,8 @@ jobs: skip-drivers: 'true' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: '' cuda-major-version: "" cuda-minor-version: "" @@ -112,12 +59,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-diffusers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'true' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: '' cuda-major-version: "" cuda-minor-version: "" @@ -125,274 +72,208 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-chatterbox' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'true' backend: "chatterbox" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - # CUDA 11 additional backends - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-kokoro' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "kokoro" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-faster-whisper' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "faster-whisper" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-coqui' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "coqui" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-bark' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "bark" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-chatterbox' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "chatterbox" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # CUDA 12 builds - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-rerankers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "rerankers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-vllm' runs-on: 'arc-runner-set' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "vllm" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-transformers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "transformers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-diffusers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-kokoro' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-faster-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "faster-whisper" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-coqui' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "coqui" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-bark' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "bark" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-chatterbox' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "chatterbox" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-stablediffusion-ggml' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-rfdetr' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-exllama2' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "exllama2" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12-neutts' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "neutts" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # cuda 13 - build-type: 'cublas' cuda-major-version: "13" @@ -401,12 +282,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-rerankers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "rerankers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -414,12 +295,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -440,12 +321,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-transformers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "transformers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -453,12 +334,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-diffusers' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'l4t' cuda-major-version: "13" cuda-minor-version: "0" @@ -471,7 +352,7 @@ jobs: ubuntu-version: '2404' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" + context: "./" - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -479,12 +360,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-kokoro' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -492,12 +373,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-faster-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "faster-whisper" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -505,12 +386,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-bark' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "bark" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -518,12 +399,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-chatterbox' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "chatterbox" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -531,12 +412,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-stablediffusion-ggml' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -557,12 +438,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "13" cuda-minor-version: "0" @@ -583,12 +464,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-13-rfdetr' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # hipblas builds - build-type: 'hipblas' cuda-major-version: "" @@ -597,12 +478,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-rerankers' runs-on: 'ubuntu-latest' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "rerankers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -610,12 +491,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -623,12 +504,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-vllm' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "vllm" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -636,12 +517,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-transformers' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "transformers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -649,12 +530,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-diffusers' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # ROCm additional backends - build-type: 'hipblas' cuda-major-version: "" @@ -663,12 +544,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-kokoro' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -676,12 +557,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-faster-whisper' runs-on: 'ubuntu-latest' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "faster-whisper" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -689,12 +570,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-coqui' runs-on: 'ubuntu-latest' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "coqui" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -702,12 +583,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-bark' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "bark" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # sycl builds - build-type: 'intel' cuda-major-version: "" @@ -720,8 +601,8 @@ jobs: skip-drivers: 'false' backend: "rerankers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'sycl_f32' cuda-major-version: "" cuda-minor-version: "" @@ -734,7 +615,7 @@ jobs: backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'sycl_f16' cuda-major-version: "" cuda-minor-version: "" @@ -747,7 +628,7 @@ jobs: backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -759,8 +640,8 @@ jobs: skip-drivers: 'false' backend: "vllm" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -772,8 +653,8 @@ jobs: skip-drivers: 'false' backend: "transformers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -785,8 +666,8 @@ jobs: skip-drivers: 'false' backend: "diffusers" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'l4t' cuda-major-version: "12" cuda-minor-version: "0" @@ -798,8 +679,8 @@ jobs: skip-drivers: 'true' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # SYCL additional backends - build-type: 'intel' cuda-major-version: "" @@ -812,8 +693,8 @@ jobs: skip-drivers: 'false' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -825,8 +706,8 @@ jobs: skip-drivers: 'false' backend: "faster-whisper" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -838,8 +719,8 @@ jobs: skip-drivers: 'false' backend: "coqui" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -851,8 +732,8 @@ jobs: skip-drivers: 'false' backend: "bark" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # piper - build-type: '' cuda-major-version: "" @@ -861,12 +742,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-piper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "piper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # bark-cpp - build-type: '' cuda-major-version: "" @@ -875,12 +756,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-bark-cpp' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "bark-cpp" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: '' cuda-major-version: "" cuda-minor-version: "" @@ -888,15 +769,15 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/arm64' skip-drivers: 'true' tag-latest: 'auto' @@ -906,7 +787,7 @@ jobs: backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'vulkan' cuda-major-version: "" cuda-minor-version: "" @@ -914,12 +795,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-vulkan-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # Stablediffusion-ggml - build-type: '' cuda-major-version: "" @@ -928,25 +809,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-stablediffusion-ggml' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "stablediffusion-ggml" - dockerfile: "./backend/Dockerfile.golang" - context: "./" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-stablediffusion-ggml' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'sycl_f32' cuda-major-version: "" cuda-minor-version: "" @@ -959,7 +827,7 @@ jobs: backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'sycl_f16' cuda-major-version: "" cuda-minor-version: "" @@ -972,7 +840,7 @@ jobs: backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'vulkan' cuda-major-version: "" cuda-minor-version: "" @@ -980,15 +848,15 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-vulkan-stablediffusion-ggml' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/arm64' skip-drivers: 'true' tag-latest: 'auto' @@ -998,7 +866,7 @@ jobs: backend: "stablediffusion-ggml" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # whisper - build-type: '' cuda-major-version: "" @@ -1007,25 +875,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "whisper" - dockerfile: "./backend/Dockerfile.golang" - context: "./" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-whisper' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'sycl_f32' cuda-major-version: "" cuda-minor-version: "" @@ -1038,7 +893,7 @@ jobs: backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'sycl_f16' cuda-major-version: "" cuda-minor-version: "" @@ -1051,7 +906,7 @@ jobs: backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'vulkan' cuda-major-version: "" cuda-minor-version: "" @@ -1059,15 +914,15 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-vulkan-whisper' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/arm64' skip-drivers: 'true' tag-latest: 'auto' @@ -1077,20 +932,20 @@ jobs: backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-whisper' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" runs-on: 'ubuntu-latest' skip-drivers: 'false' backend: "whisper" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' #silero-vad - build-type: '' cuda-major-version: "" @@ -1099,12 +954,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-silero-vad' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "silero-vad" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # local-store - build-type: '' cuda-major-version: "" @@ -1113,12 +968,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-local-store' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "local-store" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # huggingface - build-type: '' cuda-major-version: "" @@ -1127,12 +982,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-huggingface' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "huggingface" dockerfile: "./backend/Dockerfile.golang" context: "./" - ubuntu-version: '2204' + ubuntu-version: '2404' # rfdetr - build-type: '' cuda-major-version: "" @@ -1141,25 +996,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-rfdetr' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "rfdetr" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-rfdetr' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -1171,8 +1013,8 @@ jobs: skip-drivers: 'false' backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'l4t' cuda-major-version: "12" cuda-minor-version: "0" @@ -1184,8 +1026,8 @@ jobs: runs-on: 'ubuntu-24.04-arm' backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # exllama2 - build-type: '' cuda-major-version: "" @@ -1194,25 +1036,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-exllama2' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - skip-drivers: 'false' - backend: "exllama2" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11-exllama2' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "exllama2" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" @@ -1224,8 +1053,8 @@ jobs: skip-drivers: 'false' backend: "exllama2" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -1233,12 +1062,12 @@ jobs: skip-drivers: 'true' tag-latest: 'auto' tag-suffix: '-gpu-hipblas-exllama2' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" runs-on: 'ubuntu-latest' backend: "exllama2" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'l4t' cuda-major-version: "12" cuda-minor-version: "0" @@ -1250,8 +1079,8 @@ jobs: runs-on: 'ubuntu-24.04-arm' backend: "chatterbox" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # runs out of space on the runner # - build-type: 'hipblas' # cuda-major-version: "" @@ -1259,12 +1088,12 @@ jobs: # platforms: 'linux/amd64' # tag-latest: 'auto' # tag-suffix: '-gpu-hipblas-rfdetr' - # base-image: "rocm/dev-ubuntu-22.04:6.4.3" + # base-image: "rocm/dev-ubuntu-24.04:6.4.4" # runs-on: 'ubuntu-latest' # skip-drivers: 'false' # backend: "rfdetr" # dockerfile: "./backend/Dockerfile.python" - # context: "./backend" + # context: "./" # kitten-tts - build-type: '' cuda-major-version: "" @@ -1273,12 +1102,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-kitten-tts' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "kitten-tts" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' # neutts - build-type: '' cuda-major-version: "" @@ -1287,12 +1116,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-cpu-neutts' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "neutts" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'hipblas' cuda-major-version: "" cuda-minor-version: "" @@ -1300,12 +1129,12 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-rocm-hipblas-neutts' runs-on: 'arc-runner-set' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' backend: "neutts" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' - build-type: 'l4t' cuda-major-version: "12" cuda-minor-version: "0" @@ -1317,8 +1146,8 @@ jobs: runs-on: 'ubuntu-24.04-arm' backend: "neutts" dockerfile: "./backend/Dockerfile.python" - context: "./backend" - ubuntu-version: '2204' + context: "./" + ubuntu-version: '2404' backend-jobs-darwin: uses: ./.github/workflows/backend_build_darwin.yml strategy: diff --git a/.github/workflows/generate_grpc_cache.yaml b/.github/workflows/generate_grpc_cache.yaml index feadf0948bdc..72a2b306741d 100644 --- a/.github/workflows/generate_grpc_cache.yaml +++ b/.github/workflows/generate_grpc_cache.yaml @@ -16,7 +16,7 @@ jobs: strategy: matrix: include: - - grpc-base-image: ubuntu:22.04 + - grpc-base-image: ubuntu:24.04 runs-on: 'ubuntu-latest' platforms: 'linux/amd64,linux/arm64' runs-on: ${{matrix.runs-on}} diff --git a/.github/workflows/generate_intel_image.yaml b/.github/workflows/generate_intel_image.yaml index 5c0160addb38..0dc47da211ec 100644 --- a/.github/workflows/generate_intel_image.yaml +++ b/.github/workflows/generate_intel_image.yaml @@ -15,7 +15,7 @@ jobs: strategy: matrix: include: - - base-image: intel/oneapi-basekit:2025.2.0-0-devel-ubuntu22.04 + - base-image: intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04 runs-on: 'arc-runner-set' platforms: 'linux/amd64' runs-on: ${{matrix.runs-on}} diff --git a/.github/workflows/image-pr.yml b/.github/workflows/image-pr.yml index 84ffa5a1320c..2db9e5cbafa4 100644 --- a/.github/workflows/image-pr.yml +++ b/.github/workflows/image-pr.yml @@ -37,12 +37,12 @@ jobs: include: - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-gpu-nvidia-cuda-12' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" makeflags: "--jobs=3 --output-sync=target" ubuntu-version: '2204' - build-type: 'cublas' @@ -59,8 +59,8 @@ jobs: platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-hipblas' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" - grpc-base-image: "ubuntu:22.04" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" + grpc-base-image: "ubuntu:24.04" runs-on: 'ubuntu-latest' makeflags: "--jobs=3 --output-sync=target" ubuntu-version: '2204' @@ -68,7 +68,7 @@ jobs: platforms: 'linux/amd64' tag-latest: 'false' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - grpc-base-image: "ubuntu:22.04" + grpc-base-image: "ubuntu:24.04" tag-suffix: 'sycl' runs-on: 'ubuntu-latest' makeflags: "--jobs=3 --output-sync=target" @@ -78,7 +78,7 @@ jobs: tag-latest: 'false' tag-suffix: '-vulkan-core' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" makeflags: "--jobs=4 --output-sync=target" ubuntu-version: '2204' - build-type: 'cublas' diff --git a/.github/workflows/image.yml b/.github/workflows/image.yml index 7389760912c5..ad8ce97bcd4d 100644 --- a/.github/workflows/image.yml +++ b/.github/workflows/image.yml @@ -40,8 +40,8 @@ jobs: platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-hipblas' - base-image: "rocm/dev-ubuntu-22.04:6.4.3" - grpc-base-image: "ubuntu:22.04" + base-image: "rocm/dev-ubuntu-24.04:6.4.4" + grpc-base-image: "ubuntu:24.04" runs-on: 'ubuntu-latest' makeflags: "--jobs=3 --output-sync=target" aio: "-aio-gpu-hipblas" @@ -76,32 +76,20 @@ jobs: platforms: 'linux/amd64,linux/arm64' tag-latest: 'auto' tag-suffix: '' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" runs-on: 'ubuntu-latest' aio: "-aio-cpu" makeflags: "--jobs=4 --output-sync=target" skip-drivers: 'false' ubuntu-version: '2204' - - build-type: 'cublas' - cuda-major-version: "11" - cuda-minor-version: "7" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-nvidia-cuda-11' - runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" - makeflags: "--jobs=4 --output-sync=target" - skip-drivers: 'false' - aio: "-aio-gpu-nvidia-cuda-11" - ubuntu-version: '2204' - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-gpu-nvidia-cuda-12' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' makeflags: "--jobs=4 --output-sync=target" aio: "-aio-gpu-nvidia-cuda-12" @@ -123,7 +111,7 @@ jobs: tag-latest: 'auto' tag-suffix: '-gpu-vulkan' runs-on: 'ubuntu-latest' - base-image: "ubuntu:22.04" + base-image: "ubuntu:24.04" skip-drivers: 'false' makeflags: "--jobs=4 --output-sync=target" aio: "-aio-gpu-vulkan" @@ -132,7 +120,7 @@ jobs: platforms: 'linux/amd64' tag-latest: 'auto' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - grpc-base-image: "ubuntu:22.04" + grpc-base-image: "ubuntu:24.04" tag-suffix: '-gpu-intel' runs-on: 'ubuntu-latest' makeflags: "--jobs=3 --output-sync=target" @@ -165,7 +153,7 @@ jobs: include: - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "0" + cuda-minor-version: "9" platforms: 'linux/arm64' tag-latest: 'auto' tag-suffix: '-nvidia-l4t-arm64' diff --git a/.github/workflows/image_build.yml b/.github/workflows/image_build.yml index 31a1f2310ea4..39cfa1401052 100644 --- a/.github/workflows/image_build.yml +++ b/.github/workflows/image_build.yml @@ -23,7 +23,7 @@ on: type: string cuda-minor-version: description: 'CUDA minor version' - default: "4" + default: "9" type: string platforms: description: 'Platforms' diff --git a/.gitignore b/.gitignore index caae10a218a1..2ee2ab8588b1 100644 --- a/.gitignore +++ b/.gitignore @@ -25,6 +25,7 @@ go-bert # LocalAI build binary LocalAI /local-ai +/local-ai-launcher # prevent above rules from omitting the helm chart !charts/* # prevent above rules from omitting the api/localai folder diff --git a/Dockerfile b/Dockerfile index a253237c974c..8c20a702e65c 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,4 +1,4 @@ -ARG BASE_IMAGE=ubuntu:22.04 +ARG BASE_IMAGE=ubuntu:24.04 ARG GRPC_BASE_IMAGE=${BASE_IMAGE} ARG INTEL_BASE_IMAGE=${BASE_IMAGE} @@ -9,7 +9,7 @@ ENV DEBIAN_FRONTEND=noninteractive RUN apt-get update && \ apt-get install -y --no-install-recommends \ ca-certificates curl wget espeak-ng libgomp1 \ - ffmpeg && \ + ffmpeg libopenblas0 libopenblas-dev libquadmath0 && \ apt-get clean && \ rm -rf /var/lib/apt/lists/* @@ -34,11 +34,30 @@ RUN < /run/localai/capability @@ -141,13 +160,12 @@ ENV PATH=/opt/rocm/bin:${PATH} # The requirements-core target is common to all images. It should not be placed in requirements-core unless every single build will use it. FROM requirements-drivers AS build-requirements -ARG GO_VERSION=1.22.6 -ARG CMAKE_VERSION=3.26.4 +ARG GO_VERSION=1.25.4 +ARG CMAKE_VERSION=3.28.3 ARG CMAKE_FROM_SOURCE=false ARG TARGETARCH ARG TARGETVARIANT - RUN apt-get update && \ apt-get install -y --no-install-recommends \ build-essential \ @@ -206,7 +224,7 @@ WORKDIR /build FROM ${INTEL_BASE_IMAGE} AS intel RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | \ gpg --yes --dearmor --output /usr/share/keyrings/intel-graphics.gpg -RUN echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu jammy/lts/2350 unified" > /etc/apt/sources.list.d/intel-graphics.list +RUN echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu noble/lts/2350 unified" > /etc/apt/sources.list.d/intel-graphics.list RUN apt-get update && \ apt-get install -y --no-install-recommends \ intel-oneapi-runtime-libs && \ diff --git a/Dockerfile.aio b/Dockerfile.aio index 81063bb4dbeb..ccc2fc94b9ed 100644 --- a/Dockerfile.aio +++ b/Dockerfile.aio @@ -1,4 +1,4 @@ -ARG BASE_IMAGE=ubuntu:22.04 +ARG BASE_IMAGE=ubuntu:24.04 FROM ${BASE_IMAGE} diff --git a/Makefile b/Makefile index 1f855b02a673..30aa9a14bac3 100644 --- a/Makefile +++ b/Makefile @@ -1,3 +1,6 @@ +# Disable parallel execution for backend builds +.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin + GOCMD=go GOTEST=$(GOCMD) test GOVET=$(GOCMD) vet @@ -10,6 +13,8 @@ CUDA_MINOR_VERSION?=0 GORELEASER?= export BUILD_TYPE?= +export CUDA_MAJOR_VERSION?=12 +export CUDA_MINOR_VERSION?=9 GO_TAGS?= BUILD_ID?= @@ -177,7 +182,7 @@ prepare-e2e: mkdir -p $(TEST_DIR) cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin - docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=0 -t localai-tests . + docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t localai-tests . run-e2e-image: ls -liah $(abspath ./tests/e2e-fixtures) @@ -297,7 +302,7 @@ test-extra: prepare-test-extra DOCKER_IMAGE?=local-ai DOCKER_AIO_IMAGE?=local-ai-aio IMAGE_TYPE?=core -BASE_IMAGE?=ubuntu:22.04 +BASE_IMAGE?=ubuntu:24.04 docker: docker build \ @@ -308,16 +313,16 @@ docker: --build-arg BUILD_TYPE=$(BUILD_TYPE) \ -t $(DOCKER_IMAGE) . -docker-cuda11: +docker-cuda12: docker build \ - --build-arg CUDA_MAJOR_VERSION=11 \ - --build-arg CUDA_MINOR_VERSION=8 \ + --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} \ + --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} \ --build-arg BASE_IMAGE=$(BASE_IMAGE) \ --build-arg IMAGE_TYPE=$(IMAGE_TYPE) \ --build-arg GO_TAGS="$(GO_TAGS)" \ --build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \ --build-arg BUILD_TYPE=$(BUILD_TYPE) \ - -t $(DOCKER_IMAGE)-cuda-11 . + -t $(DOCKER_IMAGE)-cuda-12 . docker-aio: @echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)" @@ -358,6 +363,9 @@ backends/stablediffusion-ggml: docker-build-stablediffusion-ggml docker-save-sta backends/whisper: docker-build-whisper docker-save-whisper build ./local-ai backends install "ocifile://$(abspath ./backend-images/whisper.tar)" +backends/faster-whisper: docker-build-faster-whisper docker-save-faster-whisper build + ./local-ai backends install "ocifile://$(abspath ./backend-images/faster-whisper.tar)" + backends/silero-vad: docker-build-silero-vad docker-save-silero-vad build ./local-ai backends install "ocifile://$(abspath ./backend-images/silero-vad.tar)" @@ -419,25 +427,25 @@ backend-images: mkdir -p backend-images docker-build-llama-cpp: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:llama-cpp -f backend/Dockerfile.llama-cpp . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:llama-cpp -f backend/Dockerfile.llama-cpp . docker-build-bark-cpp: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:bark-cpp -f backend/Dockerfile.golang --build-arg BACKEND=bark-cpp . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:bark-cpp -f backend/Dockerfile.golang --build-arg BACKEND=bark-cpp . docker-build-piper: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:piper -f backend/Dockerfile.golang --build-arg BACKEND=piper . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:piper -f backend/Dockerfile.golang --build-arg BACKEND=piper . docker-build-local-store: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:local-store -f backend/Dockerfile.golang --build-arg BACKEND=local-store . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:local-store -f backend/Dockerfile.golang --build-arg BACKEND=local-store . docker-build-huggingface: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:huggingface -f backend/Dockerfile.golang --build-arg BACKEND=huggingface . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:huggingface -f backend/Dockerfile.golang --build-arg BACKEND=huggingface . docker-build-rfdetr: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:rfdetr -f backend/Dockerfile.python --build-arg BACKEND=rfdetr ./backend + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:rfdetr -f backend/Dockerfile.python --build-arg BACKEND=rfdetr . docker-build-kitten-tts: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:kitten-tts -f backend/Dockerfile.python --build-arg BACKEND=kitten-tts ./backend + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:kitten-tts -f backend/Dockerfile.python --build-arg BACKEND=kitten-tts . docker-save-kitten-tts: backend-images docker save local-ai-backend:kitten-tts -o backend-images/kitten-tts.tar @@ -446,13 +454,13 @@ docker-save-chatterbox: backend-images docker save local-ai-backend:chatterbox -o backend-images/chatterbox.tar docker-build-neutts: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:neutts -f backend/Dockerfile.python --build-arg BACKEND=neutts ./backend + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:neutts -f backend/Dockerfile.python --build-arg BACKEND=neutts . docker-save-neutts: backend-images docker save local-ai-backend:neutts -o backend-images/neutts.tar docker-build-kokoro: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:kokoro -f backend/Dockerfile.python --build-arg BACKEND=kokoro ./backend + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:kokoro -f backend/Dockerfile.python --build-arg BACKEND=kokoro . docker-build-vllm: docker build --build-arg CUDA_MAJOR_VERSION=$(CUDA_MAJOR_VERSION) --build-arg CUDA_MINOR_VERSION=$(CUDA_MINOR_VERSION) --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:vllm -f backend/Dockerfile.python --build-arg BACKEND=vllm ./backend @@ -473,7 +481,7 @@ docker-save-local-store: backend-images docker save local-ai-backend:local-store -o backend-images/local-store.tar docker-build-silero-vad: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:silero-vad -f backend/Dockerfile.golang --build-arg BACKEND=silero-vad . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:silero-vad -f backend/Dockerfile.golang --build-arg BACKEND=silero-vad . docker-save-silero-vad: backend-images docker save local-ai-backend:silero-vad -o backend-images/silero-vad.tar @@ -488,43 +496,49 @@ docker-save-bark-cpp: backend-images docker save local-ai-backend:bark-cpp -o backend-images/bark-cpp.tar docker-build-stablediffusion-ggml: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:stablediffusion-ggml -f backend/Dockerfile.golang --build-arg BACKEND=stablediffusion-ggml . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:stablediffusion-ggml -f backend/Dockerfile.golang --build-arg BACKEND=stablediffusion-ggml . docker-save-stablediffusion-ggml: backend-images docker save local-ai-backend:stablediffusion-ggml -o backend-images/stablediffusion-ggml.tar docker-build-rerankers: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:rerankers -f backend/Dockerfile.python --build-arg BACKEND=rerankers . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:rerankers -f backend/Dockerfile.python --build-arg BACKEND=rerankers . + +docker-build-vllm: + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:vllm -f backend/Dockerfile.python --build-arg BACKEND=vllm . docker-build-transformers: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:transformers -f backend/Dockerfile.python --build-arg BACKEND=transformers . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:transformers -f backend/Dockerfile.python --build-arg BACKEND=transformers . docker-build-diffusers: - docker build --progress=plain --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:diffusers -f backend/Dockerfile.python --build-arg BACKEND=diffusers ./backend + docker build --progress=plain --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:diffusers -f backend/Dockerfile.python --build-arg BACKEND=diffusers . docker-save-diffusers: backend-images docker save local-ai-backend:diffusers -o backend-images/diffusers.tar docker-build-whisper: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:whisper -f backend/Dockerfile.golang --build-arg BACKEND=whisper . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:whisper -f backend/Dockerfile.golang --build-arg BACKEND=whisper . docker-save-whisper: backend-images docker save local-ai-backend:whisper -o backend-images/whisper.tar docker-build-faster-whisper: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:faster-whisper -f backend/Dockerfile.python --build-arg BACKEND=faster-whisper . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:faster-whisper -f backend/Dockerfile.python --build-arg BACKEND=faster-whisper . + +docker-save-faster-whisper: + docker save local-ai-backend:faster-whisper -o backend-images/faster-whisper.tar docker-build-coqui: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:coqui -f backend/Dockerfile.python --build-arg BACKEND=coqui . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:coqui -f backend/Dockerfile.python --build-arg BACKEND=coqui . docker-build-bark: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:bark -f backend/Dockerfile.python --build-arg BACKEND=bark . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:bark -f backend/Dockerfile.python --build-arg BACKEND=bark . docker-build-chatterbox: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:chatterbox -f backend/Dockerfile.python --build-arg BACKEND=chatterbox ./backend + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:chatterbox -f backend/Dockerfile.python --build-arg BACKEND=chatterbox . docker-build-exllama2: - docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:exllama2 -f backend/Dockerfile.python --build-arg BACKEND=exllama2 . + docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) --build-arg CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} --build-arg CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} -t local-ai-backend:exllama2 -f backend/Dockerfile.python --build-arg BACKEND=exllama2 . docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-bark docker-build-chatterbox docker-build-exllama2 diff --git a/backend/Dockerfile.golang b/backend/Dockerfile.golang index dbfee61e2902..93c2b2ccaa47 100644 --- a/backend/Dockerfile.golang +++ b/backend/Dockerfile.golang @@ -1,4 +1,4 @@ -ARG BASE_IMAGE=ubuntu:22.04 +ARG BASE_IMAGE=ubuntu:24.04 FROM ${BASE_IMAGE} AS builder ARG BACKEND=rerankers @@ -12,7 +12,7 @@ ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} ENV DEBIAN_FRONTEND=noninteractive ARG TARGETARCH ARG TARGETVARIANT -ARG GO_VERSION=1.22.6 +ARG GO_VERSION=1.25.4 RUN apt-get update && \ apt-get install -y --no-install-recommends \ @@ -38,11 +38,30 @@ RUN <=1.24.0,<1.26.0 # https://github.com/mudler/LocalAI/pull/6240#issuecomment-3329518289 diff --git a/docker-compose.yaml b/docker-compose.yaml index b9880352ad8f..765a3fb63b2e 100644 --- a/docker-compose.yaml +++ b/docker-compose.yaml @@ -11,7 +11,7 @@ services: dockerfile: Dockerfile args: - IMAGE_TYPE=core - - BASE_IMAGE=ubuntu:22.04 + - BASE_IMAGE=ubuntu:24.04 ports: - 8080:8080 env_file: