From 36179ffbed52b3f85341b2991e0c08de04845da1 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 28 Jul 2025 15:15:19 +0200 Subject: [PATCH] fix(backend gallery): intel images for python-based backends, re-add exllama2 (#5928) chore(backend gallery): fix intel images for python-based backends Signed-off-by: Ettore Di Giacinto --- .github/workflows/backend.yml | 177 +++++++++++++---------------- backend/index.yaml | 204 +++++++++++----------------------- 2 files changed, 143 insertions(+), 238 deletions(-) diff --git a/.github/workflows/backend.yml b/.github/workflows/backend.yml index af9b1eb9c..ee8d2a53c 100644 --- a/.github/workflows/backend.yml +++ b/.github/workflows/backend.yml @@ -381,24 +381,12 @@ jobs: dockerfile: "./backend/Dockerfile.python" context: "./backend" # sycl builds - - build-type: 'sycl_f32' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-rerankers' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "rerankers" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f16' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-rerankers' + tag-suffix: '-gpu-intel-rerankers' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' @@ -429,60 +417,36 @@ jobs: backend: "llama-cpp" dockerfile: "./backend/Dockerfile.llama-cpp" context: "./" - - build-type: 'sycl_f32' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-vllm' + tag-suffix: '-gpu-intel-vllm' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' backend: "vllm" dockerfile: "./backend/Dockerfile.python" context: "./backend" - - build-type: 'sycl_f16' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-vllm' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "vllm" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f32' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-transformers' + tag-suffix: '-gpu-intel-transformers' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' backend: "transformers" dockerfile: "./backend/Dockerfile.python" context: "./backend" - - build-type: 'sycl_f16' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-transformers' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "transformers" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f32' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-diffusers' + tag-suffix: '-gpu-intel-diffusers' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' @@ -490,96 +454,48 @@ jobs: dockerfile: "./backend/Dockerfile.python" context: "./backend" # SYCL additional backends - - build-type: 'sycl_f32' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-kokoro' + tag-suffix: '-gpu-intel-kokoro' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' backend: "kokoro" dockerfile: "./backend/Dockerfile.python" context: "./backend" - - build-type: 'sycl_f16' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-kokoro' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "kokoro" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f32' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-faster-whisper' + tag-suffix: '-gpu-intel-faster-whisper' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' backend: "faster-whisper" dockerfile: "./backend/Dockerfile.python" context: "./backend" - - build-type: 'sycl_f16' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-faster-whisper' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "faster-whisper" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f32' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-coqui' + tag-suffix: '-gpu-intel-coqui' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' backend: "coqui" dockerfile: "./backend/Dockerfile.python" context: "./backend" - - build-type: 'sycl_f16' + - build-type: 'intel' cuda-major-version: "" cuda-minor-version: "" platforms: 'linux/amd64' tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-coqui' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "coqui" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f32' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f32-bark' - runs-on: 'ubuntu-latest' - base-image: "quay.io/go-skynet/intel-oneapi-base:latest" - skip-drivers: 'false' - backend: "bark" - dockerfile: "./backend/Dockerfile.python" - context: "./backend" - - build-type: 'sycl_f16' - cuda-major-version: "" - cuda-minor-version: "" - platforms: 'linux/amd64' - tag-latest: 'auto' - tag-suffix: '-gpu-intel-sycl-f16-bark' + tag-suffix: '-gpu-intel-bark' runs-on: 'ubuntu-latest' base-image: "quay.io/go-skynet/intel-oneapi-base:latest" skip-drivers: 'false' @@ -930,6 +846,67 @@ jobs: backend: "rfdetr" dockerfile: "./backend/Dockerfile.python" context: "./backend" + # exllama2 + - build-type: '' + cuda-major-version: "" + cuda-minor-version: "" + platforms: 'linux/amd64' + 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" + - build-type: 'cublas' + cuda-major-version: "12" + cuda-minor-version: "0" + platforms: 'linux/amd64' + tag-latest: 'auto' + tag-suffix: '-gpu-nvidia-cuda-12-exllama2' + runs-on: 'ubuntu-latest' + base-image: "ubuntu:22.04" + skip-drivers: 'false' + backend: "exllama2" + dockerfile: "./backend/Dockerfile.python" + context: "./backend" + - 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" + skip-drivers: 'false' + backend: "exllama2" + dockerfile: "./backend/Dockerfile.python" + context: "./backend" + - build-type: 'intel' + cuda-major-version: "" + cuda-minor-version: "" + platforms: 'linux/amd64' + tag-latest: 'auto' + tag-suffix: '-gpu-intel-exllama2' + runs-on: 'ubuntu-latest' + base-image: "quay.io/go-skynet/intel-oneapi-base:latest" + skip-drivers: 'false' + backend: "exllama2" + dockerfile: "./backend/Dockerfile.python" + context: "./backend" + - build-type: 'hipblas' + cuda-major-version: "" + cuda-minor-version: "" + platforms: 'linux/amd64' + skip-drivers: 'true' + tag-latest: 'auto' + tag-suffix: '-gpu-hipblas-exllama2' + base-image: "rocm/dev-ubuntu-22.04:6.1" + runs-on: 'ubuntu-latest' + backend: "exllama2" + dockerfile: "./backend/Dockerfile.python" + context: "./backend" # runs out of space on the runner # - build-type: 'hipblas' # cuda-major-version: "" diff --git a/backend/index.yaml b/backend/index.yaml index e93a3b4f3..17061106c 100644 --- a/backend/index.yaml +++ b/backend/index.yaml @@ -126,13 +126,13 @@ capabilities: nvidia: "cuda12-vllm" amd: "rocm-vllm" - intel: "intel-sycl-f16-vllm" + intel: "intel-vllm" - &rerankers name: "rerankers" alias: "rerankers" capabilities: nvidia: "cuda12-rerankers" - intel: "intel-sycl-f16-rerankers" + intel: "intel-rerankers" amd: "rocm-rerankers" - &transformers name: "transformers" @@ -149,7 +149,7 @@ - multimodal capabilities: nvidia: "cuda12-transformers" - intel: "intel-sycl-f16-transformers" + intel: "intel-transformers" amd: "rocm-transformers" - &diffusers name: "diffusers" @@ -166,7 +166,7 @@ alias: "diffusers" capabilities: nvidia: "cuda12-diffusers" - intel: "intel-sycl-f32-diffusers" + intel: "intel-diffusers" amd: "rocm-diffusers" - &exllama2 name: "exllama2" @@ -182,8 +182,7 @@ alias: "exllama2" capabilities: nvidia: "cuda12-exllama2" - intel: "intel-sycl-f32-exllama2" - amd: "rocm-exllama2" + intel: "intel-exllama2" - &faster-whisper icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | @@ -198,7 +197,7 @@ name: "faster-whisper" capabilities: nvidia: "cuda12-faster-whisper" - intel: "intel-sycl-f32-faster-whisper" + intel: "intel-faster-whisper" amd: "rocm-faster-whisper" - &kokoro icon: https://avatars.githubusercontent.com/u/166769057?v=4 @@ -216,7 +215,7 @@ name: "kokoro" capabilities: nvidia: "cuda12-kokoro" - intel: "intel-sycl-f32-kokoro" + intel: "intel-kokoro" amd: "rocm-kokoro" - &coqui urls: @@ -237,7 +236,7 @@ alias: "coqui" capabilities: nvidia: "cuda12-coqui" - intel: "intel-sycl-f32-coqui" + intel: "intel-coqui" amd: "rocm-coqui" icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 - &bark @@ -253,7 +252,7 @@ alias: "bark" capabilities: cuda: "cuda12-bark" - intel: "intel-sycl-f32-bark" + intel: "intel-bark" rocm: "rocm-bark" icon: https://avatars.githubusercontent.com/u/99442120?s=200&v=4 - &barkcpp @@ -644,7 +643,7 @@ capabilities: nvidia: "cuda12-vllm-development" amd: "rocm-vllm-development" - intel: "intel-sycl-f16-vllm-development" + intel: "intel-vllm-development" - !!merge <<: *vllm name: "cuda12-vllm" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm" @@ -656,15 +655,10 @@ mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-vllm - !!merge <<: *vllm - name: "intel-sycl-f32-vllm" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-vllm" + name: "intel-vllm" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-vllm" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-vllm -- !!merge <<: *vllm - name: "intel-sycl-f16-vllm" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-vllm" - mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-vllm + - localai/localai-backends:latest-gpu-intel-vllm - !!merge <<: *vllm name: "cuda12-vllm-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm" @@ -676,15 +670,10 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-vllm - !!merge <<: *vllm - name: "intel-sycl-f32-vllm-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vllm" + name: "intel-vllm-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-vllm" mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-vllm -- !!merge <<: *vllm - name: "intel-sycl-f16-vllm-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-vllm" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-vllm + - localai/localai-backends:master-gpu-intel-vllm # rfdetr - !!merge <<: *rfdetr name: "rfdetr-development" @@ -749,7 +738,7 @@ name: "rerankers-development" capabilities: nvidia: "cuda12-rerankers-development" - intel: "intel-sycl-f16-rerankers-development" + intel: "intel-rerankers-development" amd: "rocm-rerankers-development" - !!merge <<: *rerankers name: "cuda11-rerankers" @@ -762,15 +751,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-rerankers - !!merge <<: *rerankers - name: "intel-sycl-f32-rerankers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-rerankers" + name: "intel-rerankers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-rerankers" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-rerankers -- !!merge <<: *rerankers - name: "intel-sycl-f16-rerankers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-rerankers" - mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-rerankers + - 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" @@ -792,21 +776,16 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-rerankers - !!merge <<: *rerankers - name: "intel-sycl-f32-rerankers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rerankers" + name: "intel-rerankers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-rerankers" mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-rerankers -- !!merge <<: *rerankers - name: "intel-sycl-f16-rerankers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rerankers" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-rerankers + - localai/localai-backends:master-gpu-intel-rerankers ## Transformers - !!merge <<: *transformers name: "transformers-development" capabilities: nvidia: "cuda12-transformers-development" - intel: "intel-sycl-f16-transformers-development" + intel: "intel-transformers-development" amd: "rocm-transformers-development" - !!merge <<: *transformers name: "cuda12-transformers" @@ -819,15 +798,10 @@ mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-transformers - !!merge <<: *transformers - name: "intel-sycl-f32-transformers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-transformers" + name: "intel-transformers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-transformers" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-transformers -- !!merge <<: *transformers - name: "intel-sycl-f16-transformers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-transformers" - mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-transformers + - localai/localai-backends:latest-gpu-intel-transformers - !!merge <<: *transformers name: "cuda11-transformers-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-transformers" @@ -849,21 +823,16 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-transformers - !!merge <<: *transformers - name: "intel-sycl-f32-transformers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-transformers" + name: "intel-transformers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-transformers" mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-transformers -- !!merge <<: *transformers - name: "intel-sycl-f16-transformers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-transformers" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-transformers + - localai/localai-backends:master-gpu-intel-transformers ## Diffusers - !!merge <<: *diffusers name: "diffusers-development" capabilities: nvidia: "cuda12-diffusers-development" - intel: "intel-sycl-f32-diffusers-development" + intel: "intel-diffusers-development" amd: "rocm-diffusers-development" - !!merge <<: *diffusers name: "cuda12-diffusers" @@ -881,10 +850,10 @@ mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-11-diffusers - !!merge <<: *diffusers - name: "intel-sycl-f32-diffusers" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-diffusers" + name: "intel-diffusers" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-diffusers" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-diffusers + - localai/localai-backends:latest-gpu-intel-diffusers - !!merge <<: *diffusers name: "cuda11-diffusers-development" uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-diffusers" @@ -901,17 +870,16 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-diffusers - !!merge <<: *diffusers - name: "intel-sycl-f32-diffusers-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-diffusers" + name: "intel-diffusers-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-diffusers" mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-diffusers + - localai/localai-backends:master-gpu-intel-diffusers ## exllama2 - !!merge <<: *exllama2 name: "exllama2-development" capabilities: nvidia: "cuda12-exllama2-development" - intel: "intel-sycl-f32-exllama2-development" - amd: "rocm-exllama2-development" + intel: "intel-exllama2-development" - !!merge <<: *exllama2 name: "cuda11-exllama2" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-exllama2" @@ -937,7 +905,7 @@ name: "kokoro-development" capabilities: nvidia: "cuda12-kokoro-development" - intel: "intel-sycl-f32-kokoro-development" + intel: "intel-kokoro-development" amd: "rocm-kokoro-development" - !!merge <<: *kokoro name: "cuda11-kokoro-development" @@ -955,25 +923,15 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-kokoro - !!merge <<: *kokoro - name: "sycl-f32-kokoro" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-kokoro" + name: "intel-kokoro" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-kokoro" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-kokoro + - localai/localai-backends:latest-gpu-intel-kokoro - !!merge <<: *kokoro - name: "sycl-f16-kokoro" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-kokoro" + name: "intel-kokoro-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-kokoro" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-kokoro -- !!merge <<: *kokoro - name: "sycl-f16-kokoro-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-kokoro" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-kokoro -- !!merge <<: *kokoro - name: "sycl-f32-kokoro-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-kokoro" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-kokoro + - localai/localai-backends:master-gpu-intel-kokoro - !!merge <<: *kokoro name: "cuda11-kokoro" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-kokoro" @@ -994,7 +952,7 @@ name: "faster-whisper-development" capabilities: nvidia: "cuda12-faster-whisper-development" - intel: "intel-sycl-f32-faster-whisper-development" + intel: "intel-faster-whisper-development" amd: "rocm-faster-whisper-development" - !!merge <<: *faster-whisper name: "cuda11-faster-whisper" @@ -1012,32 +970,22 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-faster-whisper - !!merge <<: *faster-whisper - name: "sycl-f32-faster-whisper" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-faster-whisper" + name: "intel-faster-whisper" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-faster-whisper" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-faster-whisper + - localai/localai-backends:latest-gpu-intel-faster-whisper - !!merge <<: *faster-whisper - name: "sycl-f16-faster-whisper" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-faster-whisper" + name: "intel-faster-whisper-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-faster-whisper" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-faster-whisper -- !!merge <<: *faster-whisper - name: "sycl-f32-faster-whisper-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-faster-whisper" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-faster-whisper -- !!merge <<: *faster-whisper - name: "sycl-f16-faster-whisper-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-faster-whisper" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-faster-whisper + - localai/localai-backends:master-gpu-intel-faster-whisper ## coqui - !!merge <<: *coqui name: "coqui-development" capabilities: nvidia: "cuda12-coqui-development" - intel: "intel-sycl-f32-coqui-development" + intel: "intel-coqui-development" amd: "rocm-coqui-development" - !!merge <<: *coqui name: "cuda11-coqui" @@ -1065,25 +1013,15 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-coqui - !!merge <<: *coqui - name: "sycl-f32-coqui" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-coqui" + name: "intel-coqui" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-coqui" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-coqui + - localai/localai-backends:latest-gpu-intel-coqui - !!merge <<: *coqui - name: "sycl-f16-coqui" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-coqui" + name: "intel-coqui-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-coqui" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-coqui -- !!merge <<: *coqui - name: "sycl-f32-coqui-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-coqui" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-coqui -- !!merge <<: *coqui - name: "sycl-f16-coqui-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-coqui" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-coqui + - 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" @@ -1094,7 +1032,7 @@ name: "bark-development" capabilities: nvidia: "cuda12-bark-development" - intel: "intel-sycl-f32-bark-development" + intel: "intel-bark-development" amd: "rocm-bark-development" - !!merge <<: *bark name: "cuda11-bark-development" @@ -1112,25 +1050,15 @@ mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-bark - !!merge <<: *bark - name: "sycl-f32-bark" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bark" + name: "intel-bark" + uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-bark" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f32-bark + - localai/localai-backends:latest-gpu-intel-bark - !!merge <<: *bark - name: "sycl-f16-bark" - uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bark" + name: "intel-bark-development" + uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-bark" mirrors: - - localai/localai-backends:latest-gpu-intel-sycl-f16-bark -- !!merge <<: *bark - name: "sycl-f32-bark-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bark" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f32-bark -- !!merge <<: *bark - name: "sycl-f16-bark-development" - uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bark" - mirrors: - - localai/localai-backends:master-gpu-intel-sycl-f16-bark + - localai/localai-backends:master-gpu-intel-bark - !!merge <<: *bark name: "cuda12-bark" uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-bark"