diff --git a/.github/workflows/backend.yml b/.github/workflows/backend.yml index e47ca8be1ed5..2a4bab963a46 100644 --- a/.github/workflows/backend.yml +++ b/.github/workflows/backend.yml @@ -21,6 +21,8 @@ jobs: build-type: ${{ matrix.build-type }} cuda-major-version: ${{ matrix.cuda-major-version }} cuda-minor-version: ${{ matrix.cuda-minor-version }} + rocm-major-version: ${{ matrix.rocm-major-version }} + rocm-minor-version: ${{ matrix.rocm-minor-version }} platforms: ${{ matrix.platforms }} runs-on: ${{ matrix.runs-on }} base-image: ${{ matrix.base-image }} @@ -554,7 +556,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-rerankers' + tag-suffix: '-gpu-amd-rocm-6-rerankers' runs-on: 'ubuntu-latest' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -563,24 +565,37 @@ jobs: context: "./" ubuntu-version: '2404' - build-type: 'hipblas' - cuda-major-version: "" - cuda-minor-version: "" + rocm-major-version: "6" + rocm-minor-version: "4.3" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-llama-cpp' + tag-suffix: '-gpu-amd-rocm-6-llama-cpp' runs-on: 'ubuntu-latest' - base-image: "rocm/dev-ubuntu-24.04:6.4.4" + base-image: "ubuntu:24.04" skip-drivers: 'false' backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" ubuntu-version: '2404' + - build-type: 'hipblas' + rocm-major-version: "7" + rocm-minor-version: "1.1" + platforms: 'linux/amd64' + tag-latest: 'auto' + tag-suffix: '-gpu-amd-rocm-7-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: 'hipblas' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-vllm' + tag-suffix: '-gpu-amd-rocm-6-vllm' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -593,7 +608,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-transformers' + tag-suffix: '-gpu-amd-rocm-6-transformers' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -606,7 +621,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-diffusers' + tag-suffix: '-gpu-amd-rocm-6-diffusers' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -620,7 +635,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-kokoro' + tag-suffix: '-gpu-amd-rocm-6-kokoro' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -633,7 +648,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-vibevoice' + tag-suffix: '-gpu-amd-rocm-6-vibevoice' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -646,7 +661,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-faster-whisper' + tag-suffix: '-gpu-amd-rocm-6-faster-whisper' runs-on: 'ubuntu-latest' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -659,7 +674,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-coqui' + tag-suffix: '-gpu-amd-rocm-6-coqui' runs-on: 'ubuntu-latest' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -672,7 +687,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-bark' + tag-suffix: '-gpu-amd-rocm-6-bark' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' @@ -1055,7 +1070,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-whisper' + tag-suffix: '-gpu-amd-rocm-6-whisper' base-image: "rocm/dev-ubuntu-24.04:6.4.4" runs-on: 'ubuntu-latest' skip-drivers: 'false' @@ -1178,7 +1193,7 @@ jobs: platforms: 'linux/amd64' skip-drivers: 'true' tag-latest: 'auto' - tag-suffix: '-gpu-hipblas-exllama2' + tag-suffix: '-gpu-amd-rocm-6-exllama2' base-image: "rocm/dev-ubuntu-24.04:6.4.4" runs-on: 'ubuntu-latest' backend: "exllama2" @@ -1204,7 +1219,7 @@ jobs: # cuda-minor-version: "" # platforms: 'linux/amd64' # tag-latest: 'auto' - # tag-suffix: '-gpu-hipblas-rfdetr' + # tag-suffix: '-gpu-amd-rocm-6-rfdetr' # base-image: "rocm/dev-ubuntu-24.04:6.4.4" # runs-on: 'ubuntu-latest' # skip-drivers: 'false' @@ -1244,7 +1259,7 @@ jobs: cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-rocm-hipblas-neutts' + tag-suffix: '-gpu-amd-rocm-6-neutts' runs-on: 'arc-runner-set' base-image: "rocm/dev-ubuntu-24.04:6.4.4" skip-drivers: 'false' diff --git a/.github/workflows/backend_build.yml b/.github/workflows/backend_build.yml index e458dc3cb6b2..fa1a87e0b0a5 100644 --- a/.github/workflows/backend_build.yml +++ b/.github/workflows/backend_build.yml @@ -20,6 +20,14 @@ on: description: 'CUDA minor version' default: "1" type: string + rocm-major-version: + description: 'ROCm major version' + default: "6" + type: string + rocm-minor-version: + description: 'ROCm minor version' + default: "4.3" + type: string platforms: description: 'Platforms' default: '' diff --git a/.github/workflows/image.yml b/.github/workflows/image.yml index ce571006e510..7b7af2e8ff7b 100644 --- a/.github/workflows/image.yml +++ b/.github/workflows/image.yml @@ -1,17 +1,17 @@ --- name: 'build container images' - + on: push: branches: - master tags: - '*' - + concurrency: group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }} cancel-in-progress: true - + jobs: hipblas-jobs: uses: ./.github/workflows/image_build.yml @@ -38,17 +38,30 @@ matrix: include: - build-type: 'hipblas' + rocm-major-version: "6" + rocm-minor-version: "4.3" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-hipblas' - base-image: "rocm/dev-ubuntu-24.04:6.4.4" + tag-suffix: '-gpu-amd-rocm-6' + base-image: "ubuntu:24.04" grpc-base-image: "ubuntu:24.04" runs-on: 'ubuntu-latest' makeflags: "--jobs=3 --output-sync=target" aio: "-aio-gpu-hipblas" ubuntu-version: '2404' ubuntu-codename: 'noble' - + - build-type: 'hipblas' + rocm-major-version: "7" + rocm-minor-version: "1.1" + platforms: 'linux/amd64' + tag-latest: 'auto' + tag-suffix: '-gpu-amd-rocm-7' + base-image: "ubuntu:24.04" + runs-on: 'ubuntu-latest' + makeflags: "--jobs=3 --output-sync=target" + aio: "-aio-gpu-amd-rocm-7" + ubuntu-version: '2204' + core-image-build: uses: ./.github/workflows/image_build.yml with: @@ -134,7 +147,7 @@ aio: "-aio-gpu-intel" ubuntu-version: '2404' ubuntu-codename: 'noble' - + gh-runner: uses: ./.github/workflows/image_build.yml with: @@ -184,4 +197,3 @@ skip-drivers: 'false' ubuntu-version: '2404' ubuntu-codename: 'noble' - \ No newline at end of file diff --git a/Dockerfile b/Dockerfile index 30127f3b1da0..8d6545516634 100644 --- a/Dockerfile +++ b/Dockerfile @@ -20,6 +20,8 @@ FROM requirements AS requirements-drivers ARG BUILD_TYPE ARG CUDA_MAJOR_VERSION=12 ARG CUDA_MINOR_VERSION=0 +ARG ROCM_MAJOR_VERSION=6 +ARG ROCM_MINOR_VERSION=4.3 # ROCm version to append to the major version, in the format of their apt repo (https://repo.radeon.com/rocm/apt/). Like `0_alpha` or `3.4`. ARG SKIP_DRIVERS=false ARG TARGETARCH ARG TARGETVARIANT @@ -146,13 +148,29 @@ RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \ ; fi RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \ + # Setup for specific ROCm version as described here: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/install-methods/package-manager/package-manager-ubuntu.html + ROCM_VERSION="${ROCM_MAJOR_VERSION}.${ROCM_MINOR_VERSION}" && \ apt-get update && \ apt-get install -y --no-install-recommends \ - hipblas-dev \ - rocblas-dev && \ + gpg wget && \ + mkdir --parents --mode=0755 /etc/apt/keyrings && \ + wget -qO - https://repo.radeon.com/rocm/rocm.gpg.key | gpg --yes --dearmor --output /etc/apt/keyrings/rocm.gpg && \ + echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${ROCM_VERSION} jammy main" >> /etc/apt/sources.list.d/rocm.list && \ + if [ "${ROCM_MAJOR_VERSION}" -ge 7 ]; then \ + echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/graphics/${ROCM_VERSION}/ubuntu jammy main" >> /etc/apt/sources.list.d/rocm.list \ + ; fi && \ + echo "Package: *" >> /etc/apt/preferences.d/rocm-pin-600 && \ + echo "Pin: release o=repo.radeon.com" >> /etc/apt/preferences.d/rocm-pin-600 && \ + echo "Pin-Priority: 600" >> /etc/apt/preferences.d/rocm-pin-600 && \ + # End setup steps for specific ROCm version - the packages below will be installed from the configured repositories + apt-get update && \ + apt-get install -y --no-install-recommends \ + rocm-hip-runtime \ + rocblas-dev \ + hipblas-dev && \ apt-get clean && \ rm -rf /var/lib/apt/lists/* && \ - echo "amd" > /run/localai/capability && \ + echo "amd-rocm-${ROCM_MAJOR_VERSION}" > /run/localai/capability && \ # I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able # to locate the libraries. We run ldconfig ourselves to work around this packaging deficiency ldconfig \ diff --git a/README.md b/README.md index 092432241837..abb90194fbd7 100644 --- a/README.md +++ b/README.md @@ -43,7 +43,7 @@ > :bulb: Get help - [❓FAQ](https://localai.io/faq/) [πŸ’­Discussions](https://github.com/go-skynet/LocalAI/discussions) [:speech_balloon: Discord](https://discord.gg/uJAeKSAGDy) [:book: Documentation website](https://localai.io/) > -> [πŸ’» Quickstart](https://localai.io/basics/getting_started/) [πŸ–ΌοΈ Models](https://models.localai.io/) [πŸš€ Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap) [πŸ›« Examples](https://github.com/mudler/LocalAI-examples) Try on +> [πŸ’» Quickstart](https://localai.io/basics/getting_started/) [πŸ–ΌοΈ Models](https://models.localai.io/) [πŸš€ Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap) [πŸ›« Examples](https://github.com/mudler/LocalAI-examples) Try on [![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white)](https://t.me/localaiofficial_bot) [![tests](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml)[![Build and Release](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml)[![build container images](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml)[![Bump dependencies](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml)[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/localai)](https://artifacthub.io/packages/search?repo=localai) @@ -131,10 +131,10 @@ For more installation options, see [Installer Options](https://localai.io/instal Or run with docker: > **πŸ’‘ Docker Run vs Docker Start** -> +> > - `docker run` creates and starts a new container. If a container with the same name already exists, this command will fail. > - `docker start` starts an existing container that was previously created with `docker run`. -> +> > If you've already run LocalAI before and want to start it again, use: `docker start -i local-ai` ### CPU only image: @@ -163,7 +163,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-nv ### AMD GPU Images (ROCm): ```bash -docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-hipblas +docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-amd-rocm-6 ``` ### Intel GPU Images (oneAPI): @@ -194,7 +194,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel # AMD GPU version -docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas +docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-amd-rocm-6 ``` For more information about the AIO images and pre-downloaded models, see [Container Documentation](https://localai.io/basics/container/). @@ -254,7 +254,7 @@ Roadmap items: [List of issues](https://github.com/mudler/LocalAI/issues?q=is%3A - πŸ—£ [Text to Audio](https://localai.io/features/text-to-audio/) - πŸ”ˆ [Audio to Text](https://localai.io/features/audio-to-text/) (Audio transcription with `whisper.cpp`) - 🎨 [Image generation](https://localai.io/features/image-generation) -- πŸ”₯ [OpenAI-alike tools API](https://localai.io/features/openai-functions/) +- πŸ”₯ [OpenAI-alike tools API](https://localai.io/features/openai-functions/) - 🧠 [Embeddings generation for vector databases](https://localai.io/features/embeddings/) - ✍️ [Constrained grammars](https://localai.io/features/constrained_grammars/) - πŸ–ΌοΈ [Download Models directly from Huggingface ](https://localai.io/models/) @@ -362,7 +362,7 @@ Other: - Github bot which answer on issues, with code and documentation as context https://github.com/JackBekket/GitHelper - Github Actions: https://github.com/marketplace/actions/start-localai - Examples: https://github.com/mudler/LocalAI/tree/master/examples/ - + ### πŸ”— Resources diff --git a/backend/Dockerfile.llama-cpp b/backend/Dockerfile.llama-cpp index a93421ce37ed..009672224c3b 100644 --- a/backend/Dockerfile.llama-cpp +++ b/backend/Dockerfile.llama-cpp @@ -63,9 +63,13 @@ ARG BUILD_TYPE ENV BUILD_TYPE=${BUILD_TYPE} ARG CUDA_MAJOR_VERSION ARG CUDA_MINOR_VERSION +ARG ROCM_MAJOR_VERSION +ARG ROCM_MINOR_VERSION ARG SKIP_DRIVERS=false ENV CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} +ENV ROCM_MAJOR_VERSION=${ROCM_MAJOR_VERSION} +ENV ROCM_MINOR_VERSION=${ROCM_MINOR_VERSION} ENV DEBIAN_FRONTEND=noninteractive ARG TARGETARCH ARG TARGETVARIANT @@ -201,10 +205,27 @@ RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \ ; fi RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \ + # Setup for specific ROCm version as described here: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/install-methods/package-manager/package-manager-ubuntu.html + ROCM_VERSION="${ROCM_MAJOR_VERSION}.${ROCM_MINOR_VERSION}" && \ apt-get update && \ apt-get install -y --no-install-recommends \ - hipblas-dev \ - rocblas-dev && \ + gpg wget && \ + mkdir --parents --mode=0755 /etc/apt/keyrings && \ + wget -qO - https://repo.radeon.com/rocm/rocm.gpg.key | gpg --yes --dearmor --output /etc/apt/keyrings/rocm.gpg && \ + echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${ROCM_VERSION} jammy main" >> /etc/apt/sources.list.d/rocm.list && \ + if [ "${ROCM_MAJOR_VERSION}" -ge 7 ]; then \ + echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/graphics/${ROCM_VERSION}/ubuntu jammy main" >> /etc/apt/sources.list.d/rocm.list \ + ; fi && \ + echo "Package: *" >> /etc/apt/preferences.d/rocm-pin-600 && \ + echo "Pin: release o=repo.radeon.com" >> /etc/apt/preferences.d/rocm-pin-600 && \ + echo "Pin-Priority: 600" >> /etc/apt/preferences.d/rocm-pin-600 && \ + # End setup steps for specific ROCm version + apt-get update && \ + apt-get install -y --no-install-recommends \ + # Build dependencies + rocm-developer-tools \ + rocm-hip-runtime-dev \ + rocm-hip-sdk && \ apt-get clean && \ rm -rf /var/lib/apt/lists/* && \ # I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able diff --git a/backend/index.yaml b/backend/index.yaml index 41befc625a44..70da8dbb0a8e 100644 --- a/backend/index.yaml +++ b/backend/index.yaml @@ -21,7 +21,8 @@ default: "cpu-llama-cpp" nvidia: "cuda12-llama-cpp" intel: "intel-sycl-f16-llama-cpp" - amd: "rocm-llama-cpp" + amd-rocm-6: "rocm6-llama-cpp" + amd-rocm-7: "rocm7-llama-cpp" metal: "metal-llama-cpp" vulkan: "vulkan-llama-cpp" nvidia-l4t: "nvidia-l4t-arm64-llama-cpp" @@ -49,7 +50,7 @@ nvidia: "cuda12-whisper" intel: "intel-sycl-f16-whisper" metal: "metal-whisper" - amd: "rocm-whisper" + amd-rocm-6: "rocm6-whisper" vulkan: "vulkan-whisper" nvidia-l4t: "nvidia-l4t-arm64-whisper" nvidia-cuda-13: "cuda13-whisper" @@ -76,7 +77,7 @@ default: "cpu-stablediffusion-ggml" nvidia: "cuda12-stablediffusion-ggml" intel: "intel-sycl-f16-stablediffusion-ggml" - # amd: "rocm-stablediffusion-ggml" + # amd-rocm-6: "rocm6-stablediffusion-ggml" vulkan: "vulkan-stablediffusion-ggml" nvidia-l4t: "nvidia-l4t-arm64-stablediffusion-ggml" metal: "metal-stablediffusion-ggml" @@ -103,7 +104,7 @@ capabilities: nvidia: "cuda12-rfdetr" intel: "intel-rfdetr" - #amd: "rocm-rfdetr" + #amd-rocm-6: "rocm6-rfdetr" nvidia-l4t: "nvidia-l4t-arm64-rfdetr" default: "cpu-rfdetr" nvidia-cuda-13: "cuda13-rfdetr" @@ -139,7 +140,7 @@ alias: "vllm" capabilities: nvidia: "cuda12-vllm" - amd: "rocm-vllm" + amd-rocm-6: "rocm6-vllm" intel: "intel-vllm" nvidia-cuda-12: "cuda12-vllm" - &mlx @@ -197,7 +198,7 @@ capabilities: nvidia: "cuda12-rerankers" intel: "intel-rerankers" - amd: "rocm-rerankers" + amd-rocm-6: "rocm6-rerankers" - &transformers name: "transformers" icon: https://camo.githubusercontent.com/26569a27b8a30a488dd345024b71dbc05da7ff1b2ba97bb6080c9f1ee0f26cc7/68747470733a2f2f68756767696e67666163652e636f2f64617461736574732f68756767696e67666163652f646f63756d656e746174696f6e2d696d616765732f7265736f6c76652f6d61696e2f7472616e73666f726d6572732f7472616e73666f726d6572735f61735f615f6d6f64656c5f646566696e6974696f6e2e706e67 @@ -214,7 +215,7 @@ capabilities: nvidia: "cuda12-transformers" intel: "intel-transformers" - amd: "rocm-transformers" + amd-rocm-6: "rocm6-transformers" nvidia-cuda-13: "cuda13-transformers" nvidia-cuda-12: "cuda12-transformers" - &diffusers @@ -233,7 +234,7 @@ capabilities: nvidia: "cuda12-diffusers" intel: "intel-diffusers" - amd: "rocm-diffusers" + amd-rocm-6: "rocm6-diffusers" nvidia-l4t: "nvidia-l4t-diffusers" metal: "metal-diffusers" default: "cpu-diffusers" @@ -272,7 +273,7 @@ capabilities: nvidia: "cuda12-faster-whisper" intel: "intel-faster-whisper" - amd: "rocm-faster-whisper" + amd-rocm-6: "rocm6-faster-whisper" nvidia-cuda-13: "cuda13-faster-whisper" nvidia-cuda-12: "cuda12-faster-whisper" - &moonshine @@ -310,7 +311,7 @@ capabilities: nvidia: "cuda12-kokoro" intel: "intel-kokoro" - amd: "rocm-kokoro" + amd-rocm-6: "rocm6-kokoro" nvidia-l4t: "nvidia-l4t-kokoro" nvidia-cuda-13: "cuda13-kokoro" nvidia-cuda-12: "cuda12-kokoro" @@ -335,7 +336,7 @@ capabilities: nvidia: "cuda12-coqui" intel: "intel-coqui" - amd: "rocm-coqui" + amd-rocm-6: "rocm6-coqui" nvidia-cuda-13: "cuda13-coqui" nvidia-cuda-12: "cuda12-coqui" icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 @@ -420,7 +421,7 @@ capabilities: nvidia: "cuda12-vibevoice" intel: "intel-vibevoice" - amd: "rocm-vibevoice" + amd-rocm-6: "rocm6-vibevoice" nvidia-l4t: "nvidia-l4t-vibevoice" default: "cpu-vibevoice" nvidia-cuda-13: "cuda13-vibevoice" @@ -514,7 +515,7 @@ capabilities: default: "cpu-neutts" nvidia: "cuda12-neutts" - amd: "rocm-neutts" + amd-rocm-6: "rocm6-neutts" nvidia-l4t: "nvidia-l4t-neutts" nvidia-cuda-12: "cuda12-neutts" nvidia-l4t-cuda-12: "nvidia-l4t-arm64-neutts" @@ -523,7 +524,7 @@ capabilities: default: "cpu-neutts-development" nvidia: "cuda12-neutts-development" - amd: "rocm-neutts-development" + amd-rocm-6: "rocm6-neutts-development" nvidia-l4t: "nvidia-l4t-neutts-development" nvidia-cuda-12: "cuda12-neutts-development" nvidia-l4t-cuda-12: "nvidia-l4t-arm64-neutts-development" @@ -533,7 +534,8 @@ default: "cpu-llama-cpp-development" nvidia: "cuda12-llama-cpp-development" intel: "intel-sycl-f16-llama-cpp-development" - amd: "rocm-llama-cpp-development" + amd-rocm-6: "rocm6-llama-cpp-development" + amd-rocm-7: "rocm7-llama-cpp-development" metal: "metal-llama-cpp-development" vulkan: "vulkan-llama-cpp-development" nvidia-l4t: "nvidia-l4t-arm64-llama-cpp-development" @@ -552,10 +554,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-neutts - !!merge <<: *neutts - name: "rocm-neutts" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-neutts" + name: "rocm6-neutts" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-neutts" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-neutts + - localai/localai-backends:latest-gpu-amd-rocm-6-neutts - !!merge <<: *neutts name: "nvidia-l4t-arm64-neutts" uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-neutts" @@ -572,10 +574,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-neutts - !!merge <<: *neutts - name: "rocm-neutts-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-neutts" + name: "rocm6-neutts-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-neutts" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-neutts + - localai/localai-backends:master-gpu-amd-rocm-6-neutts - !!merge <<: *neutts name: "nvidia-l4t-arm64-neutts-development" uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-neutts" @@ -658,10 +660,15 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-llama-cpp - !!merge <<: *llamacpp - name: "rocm-llama-cpp" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-llama-cpp" + name: "rocm6-llama-cpp" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-llama-cpp" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-llama-cpp + - localai/localai-backends:latest-gpu-amd-rocm-6-llama-cpp +- !!merge <<: *llamacpp + name: "rocm7-llama-cpp" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-7-llama-cpp" + mirrors: + - localai/localai-backends:latest-gpu-amd-rocm-7-llama-cpp - !!merge <<: *llamacpp name: "intel-sycl-f32-llama-cpp" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-llama-cpp" @@ -698,10 +705,15 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-llama-cpp - !!merge <<: *llamacpp - name: "rocm-llama-cpp-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-llama-cpp" + name: "rocm6-llama-cpp-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-llama-cpp" + mirrors: + - localai/localai-backends:master-gpu-amd-rocm-6-llama-cpp +- !!merge <<: *llamacpp + name: "rocm7-llama-cpp-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-7-llama-cpp" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-llama-cpp + - localai/localai-backends:master-gpu-amd-rocm-7-llama-cpp - !!merge <<: *llamacpp name: "intel-sycl-f32-llama-cpp-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-llama-cpp" @@ -769,10 +781,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-whisper - !!merge <<: *whispercpp - name: "rocm-whisper" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-whisper" + name: "rocm6-whisper" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-whisper" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-whisper + - localai/localai-backends:latest-gpu-amd-rocm-6-whisper - !!merge <<: *whispercpp name: "intel-sycl-f32-whisper" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-whisper" @@ -809,10 +821,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-whisper - !!merge <<: *whispercpp - name: "rocm-whisper-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-whisper" + name: "rocm6-whisper-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-whisper" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-whisper + - localai/localai-backends:master-gpu-amd-rocm-6-whisper - !!merge <<: *whispercpp name: "intel-sycl-f32-whisper-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-whisper" @@ -927,7 +939,7 @@ name: "vllm-development" capabilities: nvidia: "cuda12-vllm-development" - amd: "rocm-vllm-development" + amd-rocm-6: "rocm6-vllm-development" intel: "intel-vllm-development" - !!merge <<: *vllm name: "cuda12-vllm" @@ -935,10 +947,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm - !!merge <<: *vllm - name: "rocm-vllm" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm" + name: "rocm6-vllm" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-vllm" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-vllm + - localai/localai-backends:latest-gpu-amd-rocm-6-vllm - !!merge <<: *vllm name: "intel-vllm" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-vllm" @@ -950,10 +962,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-vllm - !!merge <<: *vllm - name: "rocm-vllm-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm" + name: "rocm6-vllm-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-vllm" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-vllm + - localai/localai-backends:master-gpu-amd-rocm-6-vllm - !!merge <<: *vllm name: "intel-vllm-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-vllm" @@ -965,7 +977,7 @@ capabilities: nvidia: "cuda12-rfdetr-development" intel: "intel-rfdetr-development" - #amd: "rocm-rfdetr-development" + #amd-rocm-6: "rocm6-rfdetr-development" nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development" default: "cpu-rfdetr-development" nvidia-cuda-13: "cuda13-rfdetr-development" @@ -980,10 +992,10 @@ mirrors: - localai/localai-backends:latest-gpu-intel-rfdetr # - !!merge <<: *rfdetr -# name: "rocm-rfdetr" -# uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-hipblas-rfdetr" +# name: "rocm6-rfdetr" +# uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-rfdetr" # mirrors: -# - localai/localai-backends:latest-gpu-hipblas-rfdetr +# - localai/localai-backends:latest-gpu-amd-rocm-6-rfdetr - !!merge <<: *rfdetr name: "nvidia-l4t-arm64-rfdetr" uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-rfdetr" @@ -1010,10 +1022,10 @@ mirrors: - localai/localai-backends:master-gpu-intel-rfdetr # - !!merge <<: *rfdetr -# name: "rocm-rfdetr-development" -# uri: "quay.io/go-skynet/local-ai-backends:master-gpu-hipblas-rfdetr" +# name: "rocm6-rfdetr-development" +# uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-rfdetr" # mirrors: -# - localai/localai-backends:master-gpu-hipblas-rfdetr +# - localai/localai-backends:master-gpu-amd-rocm-6-rfdetr - !!merge <<: *rfdetr name: "cpu-rfdetr-development" uri: "quay.io/go-skynet/local-ai-backends:master-cpu-rfdetr" @@ -1040,7 +1052,7 @@ capabilities: nvidia: "cuda12-rerankers-development" intel: "intel-rerankers-development" - amd: "rocm-rerankers-development" + amd-rocm-6: "rocm6-rerankers-development" nvidia-cuda-13: "cuda13-rerankers-development" - !!merge <<: *rerankers name: "cuda12-rerankers" @@ -1053,8 +1065,8 @@ mirrors: - localai/localai-backends:latest-gpu-intel-rerankers - !!merge <<: *rerankers - name: "rocm-rerankers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-rerankers" + name: "rocm6-rerankers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-rerankers" mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-rerankers - !!merge <<: *rerankers @@ -1063,10 +1075,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-rerankers - !!merge <<: *rerankers - name: "rocm-rerankers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-rerankers" + name: "rocm6-rerankers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-rerankers" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-rerankers + - localai/localai-backends:master-gpu-amd-rocm-6-rerankers - !!merge <<: *rerankers name: "intel-rerankers-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-rerankers" @@ -1088,7 +1100,7 @@ capabilities: nvidia: "cuda12-transformers-development" intel: "intel-transformers-development" - amd: "rocm-transformers-development" + amd-rocm-6: "rocm6-transformers-development" nvidia-cuda-13: "cuda13-transformers-development" - !!merge <<: *transformers name: "cuda12-transformers" @@ -1096,10 +1108,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-transformers - !!merge <<: *transformers - name: "rocm-transformers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-transformers" + name: "rocm6-transformers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-transformers" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-transformers + - localai/localai-backends:latest-gpu-amd-rocm-6-transformers - !!merge <<: *transformers name: "intel-transformers" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-transformers" @@ -1111,10 +1123,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-transformers - !!merge <<: *transformers - name: "rocm-transformers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers" + name: "rocm6-transformers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-transformers" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-transformers + - localai/localai-backends:master-gpu-amd-rocm-6-transformers - !!merge <<: *transformers name: "intel-transformers-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-transformers" @@ -1136,7 +1148,7 @@ capabilities: nvidia: "cuda12-diffusers-development" intel: "intel-diffusers-development" - amd: "rocm-diffusers-development" + amd-rocm-6: "rocm6-diffusers-development" nvidia-l4t: "nvidia-l4t-diffusers-development" metal: "metal-diffusers-development" default: "cpu-diffusers-development" @@ -1177,8 +1189,8 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-diffusers - !!merge <<: *diffusers - name: "rocm-diffusers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-diffusers" + name: "rocm6-diffusers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-diffusers" mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-diffusers - !!merge <<: *diffusers @@ -1192,10 +1204,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-diffusers - !!merge <<: *diffusers - name: "rocm-diffusers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers" + name: "rocm6-diffusers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-diffusers" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-diffusers + - localai/localai-backends:master-gpu-amd-rocm-6-diffusers - !!merge <<: *diffusers name: "intel-diffusers-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-diffusers" @@ -1243,7 +1255,7 @@ capabilities: nvidia: "cuda12-kokoro-development" intel: "intel-kokoro-development" - amd: "rocm-kokoro-development" + amd-rocm-6: "rocm6-kokoro-development" nvidia-l4t: "nvidia-l4t-kokoro-development" - !!merge <<: *kokoro name: "cuda12-kokoro-development" @@ -1251,10 +1263,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-kokoro - !!merge <<: *kokoro - name: "rocm-kokoro-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro" + name: "rocm6-kokoro-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-kokoro" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-kokoro + - localai/localai-backends:master-gpu-amd-rocm-6-kokoro - !!merge <<: *kokoro name: "intel-kokoro" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-kokoro" @@ -1281,10 +1293,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-kokoro - !!merge <<: *kokoro - name: "rocm-kokoro" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-kokoro" + name: "rocm6-kokoro" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-kokoro" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-kokoro + - localai/localai-backends:latest-gpu-amd-rocm-6-kokoro - !!merge <<: *kokoro name: "cuda13-kokoro" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-kokoro" @@ -1301,7 +1313,7 @@ capabilities: nvidia: "cuda12-faster-whisper-development" intel: "intel-faster-whisper-development" - amd: "rocm-faster-whisper-development" + amd-rocm-6: "rocm6-faster-whisper-development" nvidia-cuda-13: "cuda13-faster-whisper-development" - !!merge <<: *faster-whisper name: "cuda12-faster-whisper-development" @@ -1309,10 +1321,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-faster-whisper - !!merge <<: *faster-whisper - name: "rocm-faster-whisper-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper" + name: "rocm6-faster-whisper-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-faster-whisper" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-faster-whisper + - localai/localai-backends:master-gpu-amd-rocm-6-faster-whisper - !!merge <<: *faster-whisper name: "intel-faster-whisper" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-faster-whisper" @@ -1378,7 +1390,7 @@ capabilities: nvidia: "cuda12-coqui-development" intel: "intel-coqui-development" - amd: "rocm-coqui-development" + amd-rocm-6: "rocm6-coqui-development" - !!merge <<: *coqui name: "cuda12-coqui" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui" @@ -1390,10 +1402,10 @@ mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-coqui - !!merge <<: *coqui - name: "rocm-coqui-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui" + name: "rocm6-coqui-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-coqui" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-coqui + - localai/localai-backends:master-gpu-amd-rocm-6-coqui - !!merge <<: *coqui name: "intel-coqui" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-coqui" @@ -1405,22 +1417,22 @@ mirrors: - localai/localai-backends:master-gpu-intel-coqui - !!merge <<: *coqui - name: "rocm-coqui" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui" + name: "rocm6-coqui" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-coqui" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-coqui + - localai/localai-backends:latest-gpu-amd-rocm-6-coqui ## bark - !!merge <<: *bark name: "bark-development" capabilities: nvidia: "cuda12-bark-development" intel: "intel-bark-development" - amd: "rocm-bark-development" + amd-rocm-6: "rocm6-bark-development" - !!merge <<: *bark - name: "rocm-bark-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bark" + name: "rocm6-bark-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-bark" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-bark + - localai/localai-backends:master-gpu-amd-rocm-6-bark - !!merge <<: *bark name: "intel-bark" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-bark" @@ -1437,10 +1449,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-bark - !!merge <<: *bark - name: "rocm-bark" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-bark" + name: "rocm6-bark" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-bark" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-bark + - localai/localai-backends:latest-gpu-amd-rocm-6-bark - !!merge <<: *bark name: "cuda12-bark-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bark" @@ -1528,7 +1540,7 @@ capabilities: nvidia: "cuda12-vibevoice-development" intel: "intel-vibevoice-development" - amd: "rocm-vibevoice-development" + amd-rocm-6: "rocm6-vibevoice-development" nvidia-l4t: "nvidia-l4t-vibevoice-development" default: "cpu-vibevoice-development" nvidia-cuda-13: "cuda13-vibevoice-development" @@ -1576,15 +1588,15 @@ mirrors: - localai/localai-backends:master-gpu-intel-vibevoice - !!merge <<: *vibevoice - name: "rocm-vibevoice" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vibevoice" + name: "rocm6-vibevoice" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-amd-rocm-6-vibevoice" mirrors: - - localai/localai-backends:latest-gpu-rocm-hipblas-vibevoice + - localai/localai-backends:latest-gpu-amd-rocm-6-vibevoice - !!merge <<: *vibevoice - name: "rocm-vibevoice-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vibevoice" + name: "rocm6-vibevoice-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-amd-rocm-6-vibevoice" mirrors: - - localai/localai-backends:master-gpu-rocm-hipblas-vibevoice + - localai/localai-backends:master-gpu-amd-rocm-6-vibevoice - !!merge <<: *vibevoice name: "nvidia-l4t-vibevoice" uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-vibevoice" diff --git a/docs/content/features/GPU-acceleration.md b/docs/content/features/GPU-acceleration.md index 2f10054d3639..d2a661ebcad0 100644 --- a/docs/content/features/GPU-acceleration.md +++ b/docs/content/features/GPU-acceleration.md @@ -182,7 +182,7 @@ The following are examples of the ROCm specific configuration elements required. ```yaml # For full functionality select a non-'core' image, version locking the image is recommended for debug purposes. - image: quay.io/go-skynet/local-ai:master-aio-gpu-hipblas + image: quay.io/go-skynet/local-ai:master-aio-gpu-amd-rocm-6 environment: - DEBUG=true # If your gpu is not already included in the current list of default targets the following build details are required. @@ -205,7 +205,7 @@ docker run \ -e GPU_TARGETS=gfx906 \ --device /dev/dri \ --device /dev/kfd \ - quay.io/go-skynet/local-ai:master-aio-gpu-hipblas + quay.io/go-skynet/local-ai:master-aio-gpu-amd-rocm-6 ``` Please ensure to add all other required environment variables, port forwardings, etc to your `compose` file or `run` command. diff --git a/docs/content/getting-started/container-images.md b/docs/content/getting-started/container-images.md index 7ea98965de4f..3d28d9ee7e78 100644 --- a/docs/content/getting-started/container-images.md +++ b/docs/content/getting-started/container-images.md @@ -84,9 +84,9 @@ Standard container images do not have pre-installed models. Use these if you wan | Description | Quay | Docker Hub | | --- | --- |-------------------------------------------------------------| -| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-hipblas` | `localai/localai:master-gpu-hipblas` | -| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-hipblas` | `localai/localai:latest-gpu-hipblas` | -| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-hipblas` | `localai/localai:{{< version >}}-gpu-hipblas` | +| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-amd-rocm-6` | `localai/localai:master-gpu-amd-rocm-6` | +| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-amd-rocm-6` | `localai/localai:latest-gpu-amd-rocm-6` | +| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-amd-rocm-6` | `localai/localai:{{< version >}}-gpu-amd-rocm-6` | {{% /tab %}} @@ -190,7 +190,7 @@ services: **Models caching**: The **AIO** image will download the needed models on the first run if not already present and store those in `/models` inside the container. The AIO models will be automatically updated with new versions of AIO images. -You can change the directory inside the container by specifying a `MODELS_PATH` environment variable (or `--models-path`). +You can change the directory inside the container by specifying a `MODELS_PATH` environment variable (or `--models-path`). If you want to use a named model or a local directory, you can mount it as a volume to `/models`: @@ -215,7 +215,7 @@ docker run -p 8080:8080 --name local-ai -ti -v localai-models:/models localai/lo | Versioned image (e.g. for CPU) | `quay.io/go-skynet/local-ai:{{< version >}}-aio-cpu` | `localai/localai:{{< version >}}-aio-cpu` | | Latest images for Nvidia GPU (CUDA12) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-12` | `localai/localai:latest-aio-gpu-nvidia-cuda-12` | | Latest images for Nvidia GPU (CUDA13) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-13` | `localai/localai:latest-aio-gpu-nvidia-cuda-13` | -| Latest images for AMD GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-hipblas` | `localai/localai:latest-aio-gpu-hipblas` | +| Latest images for AMD GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-amd-rocm-6` | `localai/localai:latest-aio-gpu-amd-rocm-6` | | Latest images for Intel GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel` | `localai/localai:latest-aio-gpu-intel` | ### Available environment variables diff --git a/docs/content/installation/docker.md b/docs/content/installation/docker.md index 7cb354f98a8a..c5b7fa574828 100644 --- a/docs/content/installation/docker.md +++ b/docs/content/installation/docker.md @@ -70,7 +70,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gp **AMD GPU (ROCm):** ```bash -docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-hipblas +docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-amd-rocm-6 ``` **Intel GPU:** @@ -119,7 +119,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai **AMD GPU (ROCm):** ```bash -docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas +docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-amd-rocm-6 ``` **Intel GPU:** @@ -140,7 +140,7 @@ services: # image: localai/localai:latest-aio-gpu-nvidia-cuda-13 # image: localai/localai:latest-aio-gpu-nvidia-cuda-12 # image: localai/localai:latest-aio-gpu-nvidia-cuda-11 - # image: localai/localai:latest-aio-gpu-hipblas + # image: localai/localai:latest-aio-gpu-amd-rocm-6 # image: localai/localai:latest-aio-gpu-intel healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"] diff --git a/docs/static/install.sh b/docs/static/install.sh index 8dfe7e4a1111..00fbb8253592 100755 --- a/docs/static/install.sh +++ b/docs/static/install.sh @@ -702,10 +702,10 @@ install_docker() { $envs \ -d -p $PORT:8080 --name local-ai localai/localai:$IMAGE_TAG $STARTCOMMAND elif [ "$HAS_AMD" ]; then - IMAGE_TAG=${LOCALAI_VERSION}-gpu-hipblas + IMAGE_TAG=${LOCALAI_VERSION}-gpu-amd-rocm-6 # AIO if [ "$USE_AIO" = true ]; then - IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-hipblas + IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-amd-rocm-6 fi info "Starting LocalAI Docker container..."