From 5cbaa5e69e09bde3334cd8c355570553a0dca027 Mon Sep 17 00:00:00 2001 From: SamareshSingh <97642706+ssam18@users.noreply.github.com> Date: Mon, 18 May 2026 15:14:45 -0500 Subject: [PATCH 1/3] docker : add OCI image labels for version and build date (#21653) * docker: add OCI image labels to all published images * docker: propagate OCI labels as manifest and index annotations * docker: drop hardcoded org URL and revert accidental intel version bump The OCI image url and source are now driven by build args with a sensible default. The workflow passes the actual repository url so fork builds get labels pointing at the fork instead of upstream. Also restores the IGC, compute runtime, and IGDGMM versions in the intel Dockerfile labeled stage which I accidentally bumped in the first commit. * docker: add skip_s390x workflow_dispatch input for fast test runs Lets maintainers and PR authors trigger the docker workflow without the s390x build target, which depends on the IBM Z runner and is by far the slowest job in the matrix. The flag filters the s390x row out of the build matrix before merge_matrix is derived, so the merge job sees a consistent shape too. Signed-off-by: Samaresh Kumar Singh --------- Signed-off-by: Samaresh Kumar Singh --- .devops/cann.Dockerfile | 16 ++++++ .devops/cpu.Dockerfile | 16 ++++++ .devops/cuda.Dockerfile | 17 +++++++ .devops/intel.Dockerfile | 16 ++++++ .devops/llama-cli-cann.Dockerfile | 17 +++++++ .devops/musa.Dockerfile | 17 +++++++ .devops/openvino.Dockerfile | 16 ++++++ .devops/rocm.Dockerfile | 17 +++++++ .devops/s390x.Dockerfile | 16 ++++++ .devops/vulkan.Dockerfile | 16 ++++++ .github/workflows/docker.yml | 83 +++++++++++++++++++++++++++++-- 11 files changed, 242 insertions(+), 5 deletions(-) diff --git a/.devops/cann.Dockerfile b/.devops/cann.Dockerfile index 843fe37d0625..acd1e26bcec8 100644 --- a/.devops/cann.Dockerfile +++ b/.devops/cann.Dockerfile @@ -5,6 +5,9 @@ # Define the CANN base image for easier version updates later ARG CHIP_TYPE=910b ARG CANN_BASE_IMAGE=quay.io/ascend/cann:8.5.0-${CHIP_TYPE}-openeuler24.03-py3.11 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A # ============================================================================== # BUILD STAGE @@ -67,6 +70,19 @@ RUN mkdir -p /app/full && \ # ============================================================================== FROM ${CANN_BASE_IMAGE} AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + # -- Install runtime dependencies -- RUN yum install -y libgomp curl && \ yum clean all && \ diff --git a/.devops/cpu.Dockerfile b/.devops/cpu.Dockerfile index d6579ecf1ad3..c8f32235d162 100644 --- a/.devops/cpu.Dockerfile +++ b/.devops/cpu.Dockerfile @@ -1,4 +1,7 @@ ARG UBUNTU_VERSION=24.04 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A FROM ubuntu:$UBUNTU_VERSION AS build @@ -35,6 +38,19 @@ RUN mkdir -p /app/full \ ## Base image FROM ubuntu:$UBUNTU_VERSION AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN apt-get update \ && apt-get install -y libgomp1 curl \ && apt autoremove -y \ diff --git a/.devops/cuda.Dockerfile b/.devops/cuda.Dockerfile index b3f6ccfc9845..3805ea3a0096 100644 --- a/.devops/cuda.Dockerfile +++ b/.devops/cuda.Dockerfile @@ -6,6 +6,10 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION} +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A + FROM ${BASE_CUDA_DEV_CONTAINER} AS build # CUDA architecture to build for (defaults to all supported archs) @@ -40,6 +44,19 @@ RUN mkdir -p /app/full \ ## Base image FROM ${BASE_CUDA_RUN_CONTAINER} AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN apt-get update \ && apt-get install -y libgomp1 curl \ && apt autoremove -y \ diff --git a/.devops/intel.Dockerfile b/.devops/intel.Dockerfile index da164dcfa5ba..218418b80b67 100644 --- a/.devops/intel.Dockerfile +++ b/.devops/intel.Dockerfile @@ -1,4 +1,7 @@ ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A ## Build Image @@ -40,6 +43,19 @@ RUN mkdir -p /app/full \ FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + ARG IGC_VERSION=v2.20.5 ARG IGC_VERSION_FULL=2_2.20.5+19972 ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10 diff --git a/.devops/llama-cli-cann.Dockerfile b/.devops/llama-cli-cann.Dockerfile index d54e70838f23..447d871ac4fb 100644 --- a/.devops/llama-cli-cann.Dockerfile +++ b/.devops/llama-cli-cann.Dockerfile @@ -1,4 +1,7 @@ ARG ASCEND_VERSION=8.5.0-910b-openeuler22.03-py3.10 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A FROM ascendai/cann:$ASCEND_VERSION AS build @@ -28,6 +31,20 @@ RUN echo "Building with static libs" && \ # TODO: use image with NNRT FROM ascendai/cann:$ASCEND_VERSION AS runtime + +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + COPY --from=build /app/build/bin/llama-cli /app/build/bin/llama-completion / ENV LC_ALL=C.utf8 diff --git a/.devops/musa.Dockerfile b/.devops/musa.Dockerfile index 665a76f58ce2..a7f70b5f0df6 100644 --- a/.devops/musa.Dockerfile +++ b/.devops/musa.Dockerfile @@ -6,6 +6,10 @@ ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_V ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A + FROM ${BASE_MUSA_DEV_CONTAINER} AS build # MUSA architecture to build for (defaults to all supported archs) @@ -45,6 +49,19 @@ RUN mkdir -p /app/full \ ## Base image FROM ${BASE_MUSA_RUN_CONTAINER} AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN apt-get update \ && apt-get install -y libgomp1 curl \ && apt autoremove -y \ diff --git a/.devops/openvino.Dockerfile b/.devops/openvino.Dockerfile index 31b58736d7e5..1266713f3788 100644 --- a/.devops/openvino.Dockerfile +++ b/.devops/openvino.Dockerfile @@ -18,6 +18,10 @@ ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2 ARG http_proxy= ARG https_proxy= +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A + ## Build Image FROM ubuntu:${UBUNTU_VERSION} AS build @@ -88,6 +92,18 @@ FROM ubuntu:${UBUNTU_VERSION} AS base # Pass proxy args to runtime stage ARG http_proxy ARG https_proxy +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE RUN apt-get update \ && apt-get install -y libgomp1 libtbb12 curl wget ocl-icd-libopencl1 \ diff --git a/.devops/rocm.Dockerfile b/.devops/rocm.Dockerfile index 525ddc790511..2da15975d13f 100644 --- a/.devops/rocm.Dockerfile +++ b/.devops/rocm.Dockerfile @@ -7,6 +7,10 @@ ARG AMDGPU_VERSION=7.2.1 # Target the ROCm build image ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A + ### Build image FROM ${BASE_ROCM_DEV_CONTAINER} AS build @@ -57,6 +61,19 @@ RUN mkdir -p /app/full \ ## Base image FROM ${BASE_ROCM_DEV_CONTAINER} AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN apt-get update \ && apt-get install -y libgomp1 curl \ && apt autoremove -y \ diff --git a/.devops/s390x.Dockerfile b/.devops/s390x.Dockerfile index 757cd97cd4cc..d36f5f3ccc5d 100644 --- a/.devops/s390x.Dockerfile +++ b/.devops/s390x.Dockerfile @@ -1,5 +1,8 @@ ARG GCC_VERSION=15.2.0 ARG UBUNTU_VERSION=24.04 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A ### Build Llama.cpp stage FROM gcc:${GCC_VERSION} AS build @@ -52,6 +55,19 @@ COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py ### Base image FROM ubuntu:${UBUNTU_VERSION} AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \ --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \ apt update -y && \ diff --git a/.devops/vulkan.Dockerfile b/.devops/vulkan.Dockerfile index f4d199ed4261..464ccfef1ce4 100644 --- a/.devops/vulkan.Dockerfile +++ b/.devops/vulkan.Dockerfile @@ -1,4 +1,7 @@ ARG UBUNTU_VERSION=26.04 +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A FROM ubuntu:$UBUNTU_VERSION AS build @@ -31,6 +34,19 @@ RUN mkdir -p /app/full \ ## Base image FROM ubuntu:$UBUNTU_VERSION AS base +ARG BUILD_DATE=N/A +ARG APP_VERSION=N/A +ARG APP_REVISION=N/A +ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp +ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp +LABEL org.opencontainers.image.created=$BUILD_DATE \ + org.opencontainers.image.version=$APP_VERSION \ + org.opencontainers.image.revision=$APP_REVISION \ + org.opencontainers.image.title="llama.cpp" \ + org.opencontainers.image.description="LLM inference in C/C++" \ + org.opencontainers.image.url=$IMAGE_URL \ + org.opencontainers.image.source=$IMAGE_SOURCE + RUN apt-get update \ && apt-get install -y libgomp1 curl libvulkan1 mesa-vulkan-drivers \ libglvnd0 libgl1 libglx0 libegl1 libgles2 \ diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml index a5bae7141fe1..6f1f2721e45f 100644 --- a/.github/workflows/docker.yml +++ b/.github/workflows/docker.yml @@ -11,6 +11,11 @@ name: Publish Docker image on: workflow_dispatch: # allows manual triggering + inputs: + skip_s390x: + description: "Skip the s390x build target (useful for fast test runs that do not need the IBM Z runner)" + type: boolean + default: false schedule: # Rebuild daily rather than on every push because it is expensive - cron: '12 4 * * *' @@ -64,6 +69,8 @@ jobs: - name: Generate build and merge matrices id: matrices shell: bash + env: + SKIP_S390X: ${{ inputs.skip_s390x || 'false' }} run: | set -euo pipefail @@ -86,6 +93,11 @@ jobs: ] JSON + if [ "${SKIP_S390X}" = "true" ]; then + jq 'map(select(.platforms != "linux/s390x"))' build-matrix.json > build-matrix.json.tmp + mv build-matrix.json.tmp build-matrix.json + fi + BUILD_MATRIX="$(jq -c . build-matrix.json)" MERGE_MATRIX="$(jq -c ' reduce .[] as $entry ({}; .[$entry.tag] |= ( @@ -132,6 +144,7 @@ jobs: config: ${{ fromJSON(needs.prepare_matrices.outputs.build_matrix) }} steps: - name: Check out the repo + id: checkout uses: actions/checkout@v6 with: fetch-depth: 0 @@ -187,6 +200,10 @@ jobs: env: GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}' + - name: Get build date + id: build_date + run: echo "date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")" >> $GITHUB_OUTPUT + - name: Free Disk Space (Ubuntu) if: ${{ matrix.config.free_disk_space == true }} uses: ggml-org/free-disk-space@v1.3.1 @@ -211,13 +228,26 @@ jobs: with: context: . platforms: ${{ matrix.config.platforms }} - outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true + outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true file: ${{ matrix.config.dockerfile }} target: full provenance: false build-args: | + BUILD_DATE=${{ steps.build_date.outputs.date }} + APP_VERSION=${{ needs.create_tag.outputs.source_tag }} + APP_REVISION=${{ steps.checkout.outputs.commit }} + IMAGE_URL=${{ github.server_url }}/${{ github.repository }} + IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }} ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }} ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }} + annotations: | + manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }} + manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }} + manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }} + manifest:org.opencontainers.image.title=llama.cpp + manifest:org.opencontainers.image.description=LLM inference in C/C++ + manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }} + manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }} # using github experimental cache #cache-from: type=gha #cache-to: type=gha,mode=max @@ -235,13 +265,26 @@ jobs: with: context: . platforms: ${{ matrix.config.platforms }} - outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true + outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true file: ${{ matrix.config.dockerfile }} target: light provenance: false build-args: | + BUILD_DATE=${{ steps.build_date.outputs.date }} + APP_VERSION=${{ needs.create_tag.outputs.source_tag }} + APP_REVISION=${{ steps.checkout.outputs.commit }} + IMAGE_URL=${{ github.server_url }}/${{ github.repository }} + IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }} ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }} ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }} + annotations: | + manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }} + manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }} + manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }} + manifest:org.opencontainers.image.title=llama.cpp + manifest:org.opencontainers.image.description=LLM inference in C/C++ + manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }} + manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }} # using github experimental cache #cache-from: type=gha #cache-to: type=gha,mode=max @@ -259,13 +302,26 @@ jobs: with: context: . platforms: ${{ matrix.config.platforms }} - outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true + outputs: type=image,name=${{ steps.meta.outputs.image_repo }},push-by-digest=true,name-canonical=true,push=true,oci-mediatypes=true file: ${{ matrix.config.dockerfile }} target: server provenance: false build-args: | + BUILD_DATE=${{ steps.build_date.outputs.date }} + APP_VERSION=${{ needs.create_tag.outputs.source_tag }} + APP_REVISION=${{ steps.checkout.outputs.commit }} + IMAGE_URL=${{ github.server_url }}/${{ github.repository }} + IMAGE_SOURCE=${{ github.server_url }}/${{ github.repository }} ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }} ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }} + annotations: | + manifest:org.opencontainers.image.created=${{ steps.build_date.outputs.date }} + manifest:org.opencontainers.image.version=${{ needs.create_tag.outputs.source_tag }} + manifest:org.opencontainers.image.revision=${{ steps.checkout.outputs.commit }} + manifest:org.opencontainers.image.title=llama.cpp + manifest:org.opencontainers.image.description=LLM inference in C/C++ + manifest:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }} + manifest:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }} # using github experimental cache #cache-from: type=gha #cache-to: type=gha,mode=max @@ -330,10 +386,15 @@ jobs: steps: - name: Check out the repo + id: checkout uses: actions/checkout@v6 with: fetch-depth: 0 + - name: Get build date + id: build_date + run: echo "date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")" >> $GITHUB_OUTPUT + - name: Download digest metadata uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8 with: @@ -361,6 +422,8 @@ jobs: IMAGE_REPO="ghcr.io/${REPO_OWNER}/${REPO_NAME}" PREFIX="${IMAGE_REPO}:" SRC_TAG="${{ needs.create_tag.outputs.source_tag }}" + BUILD_DATE="${{ steps.build_date.outputs.date }}" + COMMIT_SHA="${{ steps.checkout.outputs.commit }}" TAGS="${{ matrix.config.tag }}" ARCHES="${{ matrix.config.arches }}" DIGEST_GLOB="/tmp/digests/*.tsv" @@ -412,11 +475,21 @@ jobs: refs+=("${IMAGE_REPO}@${digest}") done + local annotations=( + --annotation "index:org.opencontainers.image.created=${BUILD_DATE}" + --annotation "index:org.opencontainers.image.version=${SRC_TAG}" + --annotation "index:org.opencontainers.image.revision=${COMMIT_SHA}" + --annotation "index:org.opencontainers.image.title=llama.cpp" + --annotation "index:org.opencontainers.image.description=LLM inference in C/C++" + --annotation "index:org.opencontainers.image.url=${{ github.server_url }}/${{ github.repository }}" + --annotation "index:org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}" + ) + echo "Creating ${merged_tag} from ${refs[*]}" - docker buildx imagetools create --tag "${merged_tag}" "${refs[@]}" + docker buildx imagetools create "${annotations[@]}" --tag "${merged_tag}" "${refs[@]}" echo "Creating ${merged_versioned_tag} from ${refs[*]}" - docker buildx imagetools create --tag "${merged_versioned_tag}" "${refs[@]}" + docker buildx imagetools create "${annotations[@]}" --tag "${merged_versioned_tag}" "${refs[@]}" } for tag in $TAGS; do From b7340443d4cf6f89e8616de87ec6b3557055e581 Mon Sep 17 00:00:00 2001 From: Pranav Dhinakar Date: Mon, 18 May 2026 13:39:36 -0700 Subject: [PATCH 2/3] ggml-hexagon: add PAD op HVX kernel (#23078) * ggml-hexagon: add PAD op HVX kernel Implements GGML_OP_PAD on the Hexagon HTP backend using HVX vectorized kernels. Supports zero-padding and circular padding across all 4 tensor dimensions. * hex-ggml: remove duplicate op cases (merge conflict) * hex-pad: fix editorconfig checks and macro alignment --------- Co-authored-by: Max Krasnyansky --- ggml/src/ggml-hexagon/ggml-hexagon.cpp | 18 + ggml/src/ggml-hexagon/htp/CMakeLists.txt | 1 + ggml/src/ggml-hexagon/htp/htp-ctx.h | 1 + ggml/src/ggml-hexagon/htp/htp-ops.h | 1 + ggml/src/ggml-hexagon/htp/main.c | 3 + ggml/src/ggml-hexagon/htp/pad-ops.c | 545 +++++++++++++++++++++++ 6 files changed, 569 insertions(+) create mode 100644 ggml/src/ggml-hexagon/htp/pad-ops.c diff --git a/ggml/src/ggml-hexagon/ggml-hexagon.cpp b/ggml/src/ggml-hexagon/ggml-hexagon.cpp index 3d1c9da83298..c24a2305e4c5 100644 --- a/ggml/src/ggml-hexagon/ggml-hexagon.cpp +++ b/ggml/src/ggml-hexagon/ggml-hexagon.cpp @@ -2744,6 +2744,18 @@ static bool ggml_hexagon_supported_ssm_conv(const struct ggml_hexagon_session * return true; } +static bool ggml_hexagon_supported_pad(const struct ggml_hexagon_session * sess, const struct ggml_tensor * op) { + const struct ggml_tensor * src0 = op->src[0]; + const struct ggml_tensor * dst = op; + + if (src0->type != GGML_TYPE_F32 || dst->type != GGML_TYPE_F32) { + return false; + } + + GGML_UNUSED(sess); + return true; +} + static bool ggml_hexagon_supported_cumsum(const struct ggml_hexagon_session * sess, const struct ggml_tensor * op) { const struct ggml_tensor * src0 = op->src[0]; const struct ggml_tensor * dst = op; @@ -2857,6 +2869,8 @@ static htp_op_code op_remap_to_htp(const ggml_tensor * t) { case GGML_OP_FILL: return HTP_OP_FILL; case GGML_OP_DIAG: return HTP_OP_DIAG; case GGML_OP_SOLVE_TRI: return HTP_OP_SOLVE_TRI; + case GGML_OP_PAD: return HTP_OP_PAD; + case GGML_OP_UNARY: switch (ggml_get_unary_op(t)) { case GGML_UNARY_OP_SILU: return HTP_OP_UNARY_SILU; @@ -3416,6 +3430,10 @@ static bool ggml_backend_hexagon_device_supports_op(ggml_backend_dev_t dev, cons supp = ggml_hexagon_supported_solve_tri(sess, op); break; + case GGML_OP_PAD: + supp = ggml_hexagon_supported_pad(sess, op); + break; + default: break; } diff --git a/ggml/src/ggml-hexagon/htp/CMakeLists.txt b/ggml/src/ggml-hexagon/htp/CMakeLists.txt index bcadac11f951..36f923243cda 100644 --- a/ggml/src/ggml-hexagon/htp/CMakeLists.txt +++ b/ggml/src/ggml-hexagon/htp/CMakeLists.txt @@ -38,6 +38,7 @@ add_library(${HTP_LIB} SHARED diag-ops.c solve-tri-ops.c gated-delta-net-ops.c + pad-ops.c ) target_compile_definitions(${HTP_LIB} PRIVATE diff --git a/ggml/src/ggml-hexagon/htp/htp-ctx.h b/ggml/src/ggml-hexagon/htp/htp-ctx.h index 92f02eac6e31..e500ce462123 100644 --- a/ggml/src/ggml-hexagon/htp/htp-ctx.h +++ b/ggml/src/ggml-hexagon/htp/htp-ctx.h @@ -107,5 +107,6 @@ int op_fill(struct htp_ops_context * octx); int op_diag(struct htp_ops_context * octx); int op_solve_tri(struct htp_ops_context * octx); int op_gated_delta_net(struct htp_ops_context * octx); +int op_pad(struct htp_ops_context * octx); #endif /* HTP_CTX_H */ diff --git a/ggml/src/ggml-hexagon/htp/htp-ops.h b/ggml/src/ggml-hexagon/htp/htp-ops.h index 98db864dd42a..985ded6f2991 100644 --- a/ggml/src/ggml-hexagon/htp/htp-ops.h +++ b/ggml/src/ggml-hexagon/htp/htp-ops.h @@ -86,6 +86,7 @@ enum htp_op_code { HTP_OP_SOLVE_TRI, HTP_OP_L2_NORM, HTP_OP_GATED_DELTA_NET, + HTP_OP_PAD, HTP_OP_INVALID }; diff --git a/ggml/src/ggml-hexagon/htp/main.c b/ggml/src/ggml-hexagon/htp/main.c index 883a31d61634..85569f072893 100644 --- a/ggml/src/ggml-hexagon/htp/main.c +++ b/ggml/src/ggml-hexagon/htp/main.c @@ -595,6 +595,9 @@ static int execute_op(struct htp_ops_context * octx) { case HTP_OP_SOLVE_TRI: return op_solve_tri(octx); + case HTP_OP_PAD: + return op_pad(octx); + case HTP_OP_GATED_DELTA_NET: return op_gated_delta_net(octx); diff --git a/ggml/src/ggml-hexagon/htp/pad-ops.c b/ggml/src/ggml-hexagon/htp/pad-ops.c new file mode 100644 index 000000000000..3abc3c2ead17 --- /dev/null +++ b/ggml/src/ggml-hexagon/htp/pad-ops.c @@ -0,0 +1,545 @@ +#pragma clang diagnostic ignored "-Wunused-variable" +#pragma clang diagnostic ignored "-Wunused-function" +#pragma clang diagnostic ignored "-Wunused-but-set-variable" + +#include +#include + +#include + +#include "hex-dma.h" +#include "hvx-utils.h" + +#define GGML_COMMON_DECL_C +#include "ggml-common.h" +#include "htp-ctx.h" +#include "htp-ops.h" + +/* Circular wrap: maps any integer x into [0, n) */ +static inline uint32_t wrap_around(int32_t x, uint32_t n) { + return (uint32_t)(((x % (int32_t)n) + (int32_t)n) % (int32_t)n); +} + +/* Decompose a flat dst row index into (i1, i2, i3) */ +static inline void pad_decompose_row(uint32_t ir, uint32_t ne1, uint32_t ne2, + uint32_t *i1, uint32_t *i2, uint32_t *i3) { + *i1 = ir % ne1; + *i2 = (ir / ne1) % ne2; + *i3 = ir / (ne1 * ne2); +} + +/* Return non-zero if row (i1,i2,i3) falls in the non-padded interior */ +static inline int pad_is_interior(uint32_t i1, uint32_t i2, uint32_t i3, + int32_t lp1, int32_t rp1, uint32_t ne1, + int32_t lp2, int32_t rp2, uint32_t ne2, + int32_t lp3, int32_t rp3, uint32_t ne3) { + return ((int32_t)i1 >= lp1 && (int32_t)i1 < (int32_t)ne1 - rp1) && + ((int32_t)i2 >= lp2 && (int32_t)i2 < (int32_t)ne2 - rp2) && + ((int32_t)i3 >= lp3 && (int32_t)i3 < (int32_t)ne3 - rp3); +} + +/* Compute the DDR src row pointer for a zero-pad interior row */ +static inline const uint8_t * pad_src_row_ptr(const struct htp_tensor * src, + uint32_t i1, uint32_t i2, uint32_t i3, + int32_t lp1, int32_t lp2, int32_t lp3) { + return (const uint8_t *) src->data + + (i1 - (uint32_t)lp1) * src->nb[1] + + (i2 - (uint32_t)lp2) * src->nb[2] + + (i3 - (uint32_t)lp3) * src->nb[3]; +} + +/* Compute the DDR src row pointer for a circular row (wrap-around indexing) */ +static inline const uint8_t * pad_circ_src_row_ptr(const struct htp_tensor * src, + uint32_t i1, uint32_t i2, uint32_t i3, + int32_t lp1, int32_t lp2, int32_t lp3) { + return (const uint8_t *) src->data + + wrap_around((int32_t)i1 - lp1, src->ne[1]) * src->nb[1] + + wrap_around((int32_t)i2 - lp2, src->ne[2]) * src->nb[2] + + wrap_around((int32_t)i3 - lp3, src->ne[3]) * src->nb[3]; +} + +struct htp_pad_context { + struct htp_ops_context * octx; + + int32_t lp0, rp0; + int32_t lp1, rp1; + int32_t lp2, rp2; + int32_t lp3, rp3; + + uint32_t nrows_per_thread; + uint32_t total_dst_rows; + + size_t type_size; + + // Row sizes for DMA kernel (populated when VTCM is available) + size_t src_row_size; + size_t src_row_size_aligned; + size_t dst_row_size; + size_t dst_row_size_aligned; +}; + +#define htp_pad_preamble \ + const struct htp_tensor * src = octx->src[0]; \ + const struct htp_tensor * dst = octx->dst; \ + \ + const uint32_t ne00 = src->ne[0]; \ + const uint32_t nb00 = src->nb[0]; \ + \ + const uint32_t ne0 = dst->ne[0]; \ + const uint32_t ne1 = dst->ne[1]; \ + const uint32_t ne2 = dst->ne[2]; \ + const uint32_t ne3 = dst->ne[3]; \ + \ + const uint32_t nb1 = dst->nb[1]; \ + const uint32_t nb2 = dst->nb[2]; \ + const uint32_t nb3 = dst->nb[3]; \ + \ + const int32_t lp0 = pctx->lp0, rp0 = pctx->rp0; \ + const int32_t lp1 = pctx->lp1, rp1 = pctx->rp1; \ + const int32_t lp2 = pctx->lp2, rp2 = pctx->rp2; \ + const int32_t lp3 = pctx->lp3, rp3 = pctx->rp3; \ + \ + const size_t type_size = pctx->type_size; \ + \ + const uint32_t row_start = pctx->nrows_per_thread * ith; \ + const uint32_t row_end = MIN(row_start + pctx->nrows_per_thread, pctx->total_dst_rows); + + +#define htp_pad_dma_preamble \ + const size_t src_row_size = pctx->src_row_size; \ + const size_t src_row_size_aligned = pctx->src_row_size_aligned; \ + const size_t dst_row_size = pctx->dst_row_size; \ + const size_t dst_row_size_aligned = pctx->dst_row_size_aligned; \ + \ + uint8_t * src_spad_base = octx->src0_spad.data + ith * octx->src0_spad.size_per_thread; \ + uint8_t * dst_spad_base = octx->dst_spad.data + ith * octx->dst_spad.size_per_thread; \ + \ + dma_queue * dma = octx->ctx->dma[ith]; + +// --------------------------------------------------------------------------- +// HVX vectorized PAD kernel +// --------------------------------------------------------------------------- + +static void pad_job_per_thread_hvx(unsigned int nth, unsigned int ith, void * data) { + const struct htp_pad_context * pctx = (const struct htp_pad_context *) data; + struct htp_ops_context * octx = pctx->octx; + htp_pad_preamble; + + uint64_t t1, t2; + t1 = HAP_perf_get_qtimer_count(); + + for (uint32_t dst_row = row_start; dst_row < row_end; dst_row++) { + uint32_t i1, i2, i3; + pad_decompose_row(dst_row, ne1, ne2, &i1, &i2, &i3); + + uint8_t * dst_ptr = (uint8_t *) dst->data + i1 * nb1 + i2 * nb2 + i3 * nb3; + + const int interior = pad_is_interior(i1, i2, i3, + lp1, rp1, ne1, + lp2, rp2, ne2, + lp3, rp3, ne3); + + if (!interior) { + hvx_splat_f32_u(dst_ptr, 0.0f, ne0); + } else { + const uint8_t * src_ptr = pad_src_row_ptr(src, i1, i2, i3, lp1, lp2, lp3); + + if (lp0 > 0) { + hvx_splat_f32_u(dst_ptr, 0.0f, (uint32_t)lp0); + } + + uint8_t * dst_row_start = dst_ptr + (size_t)lp0 * type_size; + if (nb00 == type_size) { + hvx_copy_f32_uu(dst_row_start, src_ptr, ne00); + } else { + for (uint32_t i = 0; i < ne00; i++) { + memcpy(dst_row_start + i * type_size, + src_ptr + (size_t)i * nb00, + type_size); + } + } + + if (rp0 > 0) { + hvx_splat_f32_u(dst_ptr + ((size_t)lp0 + ne00) * type_size, 0.0f, (uint32_t)rp0); + } + } + } + + t2 = HAP_perf_get_qtimer_count(); + + FARF(HIGH, "pad-hvx %d/%d: (%ux%ux%ux%u) -> (%ux%ux%ux%u) rows %u:%u usec %u\n", + ith, nth, + src->ne[0], src->ne[1], src->ne[2], src->ne[3], + dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], + row_start, row_end, + (unsigned) HAP_perf_qtimer_count_to_us(t2 - t1)); +} + +// --------------------------------------------------------------------------- +// HVX + DMA PAD kernel — aligned, double-buffered +// --------------------------------------------------------------------------- + +static void pad_job_per_thread_hvx_dma(unsigned int nth, unsigned int ith, void * data) { + const struct htp_pad_context * pctx = (const struct htp_pad_context *) data; + struct htp_ops_context * octx = pctx->octx; + htp_pad_preamble; + htp_pad_dma_preamble; + + uint64_t t1, t2; + t1 = HAP_perf_get_qtimer_count(); + + // ----------------------------------------------------------------------- + // Priming phase: push 2 pairs of (dummy_dst_DMA, src_DMA) to seed the + // double-buffer pipeline before the main loop begins. + // ----------------------------------------------------------------------- + for (uint32_t ir = row_start, spad_idx = 0; ir < row_end && spad_idx < 2; ir++, spad_idx++) { + uint8_t * src_spad_cur = src_spad_base + spad_idx * src_row_size_aligned; + uint8_t * dst_spad_cur = dst_spad_base + spad_idx * dst_row_size_aligned; + + dma_queue_push_vtcm_to_ddr(dma, + dma_make_ptr((uint8_t *)dst->data, dst_spad_cur), + dst_row_size, dst_row_size_aligned, 0); + + uint32_t i1, i2, i3; + pad_decompose_row(ir, ne1, ne2, &i1, &i2, &i3); + const int interior = pad_is_interior(i1, i2, i3, + lp1, rp1, ne1, + lp2, rp2, ne2, + lp3, rp3, ne3); + + const uint8_t * src_ptr = interior + ? pad_src_row_ptr(src, i1, i2, i3, lp1, lp2, lp3) : NULL; + + // Interior row: real DMA (1 row) from DDR to VTCM. + // Border row: null DMA (nrows=0) + dma_queue_push_ddr_to_vtcm(dma, + dma_make_ptr(src_spad_cur, + src_ptr ? src_ptr : (const uint8_t *)src_spad_cur), + src_row_size_aligned, src_row_size, src_ptr ? 1 : 0); + } + + // ----------------------------------------------------------------------- + // Main loop: pop completed DMAs, compute in VTCM with aligned HVX ops, + // push dst DMA and prefetch src for the next+1 row. + // ----------------------------------------------------------------------- + for (uint32_t ir = row_start; ir < row_end; ir++) { + uint8_t * dst_spad_cur = (uint8_t *) dma_queue_pop(dma).src; + uint8_t * src_spad_cur = (uint8_t *) dma_queue_pop(dma).dst; + + uint32_t i1, i2, i3; + pad_decompose_row(ir, ne1, ne2, &i1, &i2, &i3); + + uint8_t * dst_ptr = (uint8_t *) dst->data + i1 * nb1 + i2 * nb2 + i3 * nb3; + + const int interior = pad_is_interior(i1, i2, i3, + lp1, rp1, ne1, + lp2, rp2, ne2, + lp3, rp3, ne3); + + if (!interior) { + hvx_splat_f32_a(dst_spad_cur, 0.0f, ne0); + } else { + hvx_splat_f32_a(dst_spad_cur, 0.0f, ne0); + + uint8_t * dst_interior = dst_spad_cur + (size_t)lp0 * type_size; + + if ((uintptr_t)dst_interior % VLEN == 0) { + hvx_copy_f32_aa(dst_interior, src_spad_cur, ne00); + } else { + hvx_copy_f32_ua(dst_interior, src_spad_cur, ne00); + } + } + + dma_queue_push_vtcm_to_ddr(dma, + dma_make_ptr(dst_ptr, dst_spad_cur), + dst_row_size, dst_row_size_aligned, 1); + + const uint32_t next_row = ir + 2; + if (next_row < row_end) { + uint32_t ni1, ni2, ni3; + pad_decompose_row(next_row, ne1, ne2, &ni1, &ni2, &ni3); + const int next_interior = pad_is_interior(ni1, ni2, ni3, + lp1, rp1, ne1, + lp2, rp2, ne2, + lp3, rp3, ne3); + const uint8_t * next_src_ptr = next_interior + ? pad_src_row_ptr(src, ni1, ni2, ni3, lp1, lp2, lp3) : NULL; + + dma_queue_push_ddr_to_vtcm(dma, + dma_make_ptr(src_spad_cur, + next_src_ptr ? next_src_ptr : (const uint8_t *)src_spad_cur), + src_row_size_aligned, src_row_size, next_src_ptr ? 1 : 0); + } + } + + dma_queue_flush(dma); + + t2 = HAP_perf_get_qtimer_count(); + + FARF(HIGH, "pad-hvx-dma %d/%d: (%ux%ux%ux%u) -> (%ux%ux%ux%u) rows %u:%u usec %u\n", + ith, nth, + src->ne[0], src->ne[1], src->ne[2], src->ne[3], + dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], + row_start, row_end, + (unsigned) HAP_perf_qtimer_count_to_us(t2 - t1)); +} + +// --------------------------------------------------------------------------- +// HVX circular PAD kernel +// --------------------------------------------------------------------------- + +static void pad_job_per_thread_hvx_circular(unsigned int nth, unsigned int ith, void * data) { + const struct htp_pad_context * pctx = (const struct htp_pad_context *) data; + struct htp_ops_context * octx = pctx->octx; + htp_pad_preamble; + + uint64_t t1, t2; + t1 = HAP_perf_get_qtimer_count(); + + for (uint32_t dst_row = row_start; dst_row < row_end; dst_row++) { + uint32_t i1, i2, i3; + pad_decompose_row(dst_row, ne1, ne2, &i1, &i2, &i3); + + uint8_t * dst_ptr = (uint8_t *) dst->data + i1 * nb1 + i2 * nb2 + i3 * nb3; + const uint8_t * src_row = pad_circ_src_row_ptr(src, i1, i2, i3, lp1, lp2, lp3); + + if (nb00 == type_size) { + + if (lp0 > 0) { + if ((uint32_t)lp0 < 32) { + memcpy(dst_ptr, + src_row + (size_t)(ne00 - (uint32_t)lp0) * type_size, + (size_t)lp0 * type_size); + } else { + hvx_copy_f32_uu(dst_ptr, + src_row + (size_t)(ne00 - (uint32_t)lp0) * type_size, + (uint32_t)lp0); + } + } + hvx_copy_f32_uu(dst_ptr + (size_t)lp0 * type_size, src_row, ne00); + if (rp0 > 0) { + if ((uint32_t)rp0 < 32) { + memcpy(dst_ptr + ((size_t)lp0 + ne00) * type_size, + src_row, + (size_t)rp0 * type_size); + } else { + hvx_copy_f32_uu(dst_ptr + ((size_t)lp0 + ne00) * type_size, + src_row, + (uint32_t)rp0); + } + } + } else { + for (uint32_t i = 0; i < (uint32_t)lp0; i++) { + *(float *)(dst_ptr + i * type_size) = + *(const float *)(src_row + (size_t)(ne00 - (uint32_t)lp0 + i) * nb00); + } + for (uint32_t i = 0; i < ne00; i++) { + *(float *)(dst_ptr + ((size_t)lp0 + i) * type_size) = + *(const float *)(src_row + (size_t)i * nb00); + } + for (uint32_t i = 0; i < (uint32_t)rp0; i++) { + *(float *)(dst_ptr + ((size_t)lp0 + ne00 + i) * type_size) = + *(const float *)(src_row + (size_t)i * nb00); + } + } + } + + t2 = HAP_perf_get_qtimer_count(); + + FARF(HIGH, "pad-hvx-circ %d/%d: (%ux%ux%ux%u) -> (%ux%ux%ux%u) rows %u:%u usec %u\n", + ith, nth, + src->ne[0], src->ne[1], src->ne[2], src->ne[3], + dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], + row_start, row_end, + (unsigned) HAP_perf_qtimer_count_to_us(t2 - t1)); +} + +// --------------------------------------------------------------------------- +// HVX + DMA circular PAD kernel — aligned, double-buffered +// --------------------------------------------------------------------------- + +static void pad_job_per_thread_hvx_circular_dma(unsigned int nth, unsigned int ith, void * data) { + const struct htp_pad_context * pctx = (const struct htp_pad_context *) data; + struct htp_ops_context * octx = pctx->octx; + htp_pad_preamble; + htp_pad_dma_preamble; + + uint64_t t1, t2; + t1 = HAP_perf_get_qtimer_count(); + + // ----------------------------------------------------------------------- + // Priming phase: push 2 pairs of (dummy_dst_DMA, src_DMA) to seed the + // double-buffer pipeline. Every row is a real src DMA (no null DMAs). + // ----------------------------------------------------------------------- + for (uint32_t ir = row_start, spad_idx = 0; ir < row_end && spad_idx < 2; ir++, spad_idx++) { + uint8_t * src_spad_cur = src_spad_base + spad_idx * src_row_size_aligned; + uint8_t * dst_spad_cur = dst_spad_base + spad_idx * dst_row_size_aligned; + + dma_queue_push_vtcm_to_ddr(dma, + dma_make_ptr((uint8_t *)dst->data, dst_spad_cur), + dst_row_size, dst_row_size_aligned, 0); + + uint32_t pi1, pi2, pi3; + pad_decompose_row(ir, ne1, ne2, &pi1, &pi2, &pi3); + dma_queue_push_ddr_to_vtcm(dma, + dma_make_ptr(src_spad_cur, pad_circ_src_row_ptr(src, pi1, pi2, pi3, lp1, lp2, lp3)), + src_row_size_aligned, src_row_size, 1); + } + + // ----------------------------------------------------------------------- + // Main loop: pop completed DMAs, assemble circular row in VTCM with + // aligned HVX ops, push dst DMA and prefetch src for the next+1 row. + // ----------------------------------------------------------------------- + for (uint32_t ir = row_start; ir < row_end; ir++) { + uint8_t * dst_spad_cur = (uint8_t *) dma_queue_pop(dma).src; + uint8_t * src_spad_cur = (uint8_t *) dma_queue_pop(dma).dst; + + uint32_t i1, i2, i3; + pad_decompose_row(ir, ne1, ne2, &i1, &i2, &i3); + uint8_t * dst_ptr = (uint8_t *) dst->data + i1 * nb1 + i2 * nb2 + i3 * nb3; + + + if (lp0 > 0) { + uint8_t * dst_left = dst_spad_cur; + const uint8_t * src_left = src_spad_cur + (size_t)(ne00 - (uint32_t)lp0) * type_size; + if ((uint32_t)lp0 < 32) { + memcpy(dst_left, src_left, (size_t)lp0 * type_size); + } else { + hvx_copy_f32_uu(dst_left, src_left, (uint32_t)lp0); + } + } + + { + uint8_t * dst_mid = dst_spad_cur + (size_t)lp0 * type_size; + if ((uintptr_t)dst_mid % VLEN == 0) { + hvx_copy_f32_aa(dst_mid, src_spad_cur, ne00); + } else { + hvx_copy_f32_ua(dst_mid, src_spad_cur, ne00); + } + } + + if (rp0 > 0) { + uint8_t * dst_right = dst_spad_cur + ((size_t)lp0 + ne00) * type_size; + if ((uint32_t)rp0 < 32) { + memcpy(dst_right, src_spad_cur, (size_t)rp0 * type_size); + } else { + if ((uintptr_t)dst_right % VLEN == 0) { + hvx_copy_f32_aa(dst_right, src_spad_cur, (uint32_t)rp0); + } else { + hvx_copy_f32_ua(dst_right, src_spad_cur, (uint32_t)rp0); + } + } + } + + dma_queue_push_vtcm_to_ddr(dma, + dma_make_ptr(dst_ptr, dst_spad_cur), + dst_row_size, dst_row_size_aligned, 1); + + const uint32_t next_row = ir + 2; + if (next_row < row_end) { + uint32_t nri1, nri2, nri3; + pad_decompose_row(next_row, ne1, ne2, &nri1, &nri2, &nri3); + dma_queue_push_ddr_to_vtcm(dma, + dma_make_ptr(src_spad_cur, + pad_circ_src_row_ptr(src, nri1, nri2, nri3, lp1, lp2, lp3)), + src_row_size_aligned, src_row_size, 1); + } + } + + dma_queue_flush(dma); + + t2 = HAP_perf_get_qtimer_count(); + + FARF(HIGH, "pad-hvx-circ-dma %d/%d: (%ux%ux%ux%u) -> (%ux%ux%ux%u) rows %u:%u usec %u\n", + ith, nth, + src->ne[0], src->ne[1], src->ne[2], src->ne[3], + dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], + row_start, row_end, + (unsigned) HAP_perf_qtimer_count_to_us(t2 - t1)); +} + +int op_pad(struct htp_ops_context * octx) { + const struct htp_tensor * src0 = octx->src[0]; + const struct htp_tensor * dst = octx->dst; + + // Only F32 supported + size_t type_size; + switch (src0->type) { + case HTP_TYPE_F32: type_size = 4; break; + default: + FARF(ERROR, "pad-hvx: unsupported type %u\n", src0->type); + return HTP_STATUS_NO_SUPPORT; + } + + if (octx->flags & HTP_OPFLAGS_SKIP_COMPUTE) { + return HTP_STATUS_OK; + } + + const int32_t lp0 = octx->op_params[0]; + const int32_t rp0 = octx->op_params[1]; + const int32_t lp1 = octx->op_params[2]; + const int32_t rp1 = octx->op_params[3]; + const int32_t lp2 = octx->op_params[4]; + const int32_t rp2 = octx->op_params[5]; + const int32_t lp3 = octx->op_params[6]; + const int32_t rp3 = octx->op_params[7]; + const int32_t circular = octx->op_params[8]; + + const uint32_t ne0 = dst->ne[0]; + const uint32_t ne00 = src0->ne[0]; + + const uint32_t total_dst_rows = dst->ne[1] * dst->ne[2] * dst->ne[3]; + const uint32_t n_threads = MIN(octx->n_threads, total_dst_rows > 0 ? total_dst_rows : 1); + + const size_t src_row_size = (size_t)ne00 * type_size; + const size_t dst_row_size = (size_t)ne0 * type_size; + const size_t src_row_size_aligned = hex_round_up(src_row_size, VLEN); + const size_t dst_row_size_aligned = hex_round_up(dst_row_size, VLEN); + + // Total VTCM needed: 2 buffers (ping+pong) for src and dst, per thread + const size_t vtcm_needed = (size_t)n_threads * 2 * (src_row_size_aligned + dst_row_size_aligned); + + const int use_dma = (src0->nb[0] == (uint32_t)type_size) && + (ne00 >= 512) && + (octx->ctx->vtcm_base != NULL) && + (octx->ctx->vtcm_size >= vtcm_needed); + + if (use_dma) { + octx->src0_spad.size_per_thread = 2 * src_row_size_aligned; + octx->dst_spad.size_per_thread = 2 * dst_row_size_aligned; + octx->src0_spad.size = n_threads * octx->src0_spad.size_per_thread; + octx->dst_spad.size = n_threads * octx->dst_spad.size_per_thread; + octx->src0_spad.data = octx->ctx->vtcm_base; + octx->dst_spad.data = octx->src0_spad.data + octx->src0_spad.size; + } + + struct htp_pad_context pctx = { + .octx = octx, + .lp0 = lp0, .rp0 = rp0, + .lp1 = lp1, .rp1 = rp1, + .lp2 = lp2, .rp2 = rp2, + .lp3 = lp3, .rp3 = rp3, + .nrows_per_thread = (total_dst_rows + n_threads - 1) / n_threads, + .total_dst_rows = total_dst_rows, + .type_size = type_size, + .src_row_size = src_row_size, + .src_row_size_aligned = src_row_size_aligned, + .dst_row_size = dst_row_size, + .dst_row_size_aligned = dst_row_size_aligned, + }; + + FARF(HIGH, "pad-hvx%s%s: (%ux%ux%ux%u) -> (%ux%ux%ux%u) pads=(%d,%d,%d,%d,%d,%d,%d,%d)\n", + circular ? "-circ" : "", + use_dma ? "-dma" : "", + src0->ne[0], src0->ne[1], src0->ne[2], src0->ne[3], + dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], + lp0, rp0, lp1, rp1, lp2, rp2, lp3, rp3); + + if (circular && use_dma) { worker_pool_run_func(octx->ctx->worker_pool, pad_job_per_thread_hvx_circular_dma, &pctx, n_threads); } + else if (circular) { worker_pool_run_func(octx->ctx->worker_pool, pad_job_per_thread_hvx_circular, &pctx, n_threads); } + else if (use_dma) { worker_pool_run_func(octx->ctx->worker_pool, pad_job_per_thread_hvx_dma, &pctx, n_threads); } + else { worker_pool_run_func(octx->ctx->worker_pool, pad_job_per_thread_hvx, &pctx, n_threads); } + + return HTP_STATUS_OK; +} + From 9a532ae4bab1b164052ce60a738f78538b421c66 Mon Sep 17 00:00:00 2001 From: Pranav Dhinakar Date: Mon, 18 May 2026 14:04:57 -0700 Subject: [PATCH 3/3] hexagon: add support for TRI op (#22822) * Hexagon: TRI HVX Kernel addition to ggml hexagon HTP ops and context * addressed PR review comments for TRI op * hexagon: clang format * hex-unary: remove merge conflict markers * hex-ggml: remove duplicate op cases (merge conflict) * hex-ggml: fix editor config errors --------- Co-authored-by: Todor Boinovski Co-authored-by: Max Krasnyansky --- ggml/src/ggml-hexagon/ggml-hexagon.cpp | 20 +++++ ggml/src/ggml-hexagon/htp/htp-ctx.h | 1 + ggml/src/ggml-hexagon/htp/htp-ops.h | 1 + ggml/src/ggml-hexagon/htp/main.c | 3 + ggml/src/ggml-hexagon/htp/unary-ops.c | 113 ++++++++++++++++++++++++- 5 files changed, 137 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-hexagon/ggml-hexagon.cpp b/ggml/src/ggml-hexagon/ggml-hexagon.cpp index c24a2305e4c5..2f75e97ac66e 100644 --- a/ggml/src/ggml-hexagon/ggml-hexagon.cpp +++ b/ggml/src/ggml-hexagon/ggml-hexagon.cpp @@ -2828,6 +2828,21 @@ static bool ggml_hexagon_supported_solve_tri(const struct ggml_hexagon_session * return true; } +static bool ggml_hexagon_supported_tri(const struct ggml_hexagon_session * sess, const struct ggml_tensor * op) { + + const struct ggml_tensor * src0 = op->src[0]; + const struct ggml_tensor * dst = op; + + if (src0->type != GGML_TYPE_F32) { return false; } + if (dst->type != GGML_TYPE_F32) { return false; } + if (!ggml_are_same_shape(src0, dst)) { return false; } + if (!ggml_is_contiguous(src0) || !ggml_is_contiguous(dst)) { return false; } + + return true; + + GGML_UNUSED(sess); +} + static const char * ggml_backend_hexagon_name(ggml_backend_t backend) { auto sess = static_cast(backend->context); return sess->c_name(); @@ -2869,6 +2884,7 @@ static htp_op_code op_remap_to_htp(const ggml_tensor * t) { case GGML_OP_FILL: return HTP_OP_FILL; case GGML_OP_DIAG: return HTP_OP_DIAG; case GGML_OP_SOLVE_TRI: return HTP_OP_SOLVE_TRI; + case GGML_OP_TRI: return HTP_OP_TRI; case GGML_OP_PAD: return HTP_OP_PAD; case GGML_OP_UNARY: @@ -3430,6 +3446,10 @@ static bool ggml_backend_hexagon_device_supports_op(ggml_backend_dev_t dev, cons supp = ggml_hexagon_supported_solve_tri(sess, op); break; + case GGML_OP_TRI: + supp = ggml_hexagon_supported_tri(sess, op); + break; + case GGML_OP_PAD: supp = ggml_hexagon_supported_pad(sess, op); break; diff --git a/ggml/src/ggml-hexagon/htp/htp-ctx.h b/ggml/src/ggml-hexagon/htp/htp-ctx.h index e500ce462123..6fe3e6c7d85a 100644 --- a/ggml/src/ggml-hexagon/htp/htp-ctx.h +++ b/ggml/src/ggml-hexagon/htp/htp-ctx.h @@ -107,6 +107,7 @@ int op_fill(struct htp_ops_context * octx); int op_diag(struct htp_ops_context * octx); int op_solve_tri(struct htp_ops_context * octx); int op_gated_delta_net(struct htp_ops_context * octx); +int op_tri(struct htp_ops_context * octx); int op_pad(struct htp_ops_context * octx); #endif /* HTP_CTX_H */ diff --git a/ggml/src/ggml-hexagon/htp/htp-ops.h b/ggml/src/ggml-hexagon/htp/htp-ops.h index 985ded6f2991..676e948a4398 100644 --- a/ggml/src/ggml-hexagon/htp/htp-ops.h +++ b/ggml/src/ggml-hexagon/htp/htp-ops.h @@ -86,6 +86,7 @@ enum htp_op_code { HTP_OP_SOLVE_TRI, HTP_OP_L2_NORM, HTP_OP_GATED_DELTA_NET, + HTP_OP_TRI, HTP_OP_PAD, HTP_OP_INVALID diff --git a/ggml/src/ggml-hexagon/htp/main.c b/ggml/src/ggml-hexagon/htp/main.c index 85569f072893..12003c1fd8a4 100644 --- a/ggml/src/ggml-hexagon/htp/main.c +++ b/ggml/src/ggml-hexagon/htp/main.c @@ -601,6 +601,9 @@ static int execute_op(struct htp_ops_context * octx) { case HTP_OP_GATED_DELTA_NET: return op_gated_delta_net(octx); + case HTP_OP_TRI: + return op_tri(octx); + case HTP_OP_INVALID: break; diff --git a/ggml/src/ggml-hexagon/htp/unary-ops.c b/ggml/src/ggml-hexagon/htp/unary-ops.c index d4ae89ee6f04..1ce881353ec9 100644 --- a/ggml/src/ggml-hexagon/htp/unary-ops.c +++ b/ggml/src/ggml-hexagon/htp/unary-ops.c @@ -17,7 +17,6 @@ #include "ggml-common.h" #include "htp-ctx.h" #include "htp-ops.h" -#include "htp-ops.h" struct htp_unary_context { struct htp_ops_context * octx; @@ -277,6 +276,95 @@ static void sigmoid_f32(const float * restrict src, } } +static void tri_f32(const float * restrict src, + float * restrict dst, + uint8_t * restrict spad, + const uint32_t num_rows, + const uint32_t row_elems, + const size_t row_size, + int32_t * op_params, + const uint32_t ir, + const struct htp_unary_context * uctx) { + + const int32_t ttype = op_params[0]; + const HVX_Vector zero = hvx_vec_splat_f32(0.0f); + const uint32_t nvec = row_elems / VLEN_FP32; + const uint32_t nloe = row_elems % VLEN_FP32; + + const uint32_t ne01 = uctx->octx->src[0]->ne[1]; + + for (uint32_t b = 0; b < num_rows; b++) { + const uint32_t abs_row = ir + b; + const uint32_t i01 = abs_row % ne01; + + const HVX_Vector * restrict v_src = (const HVX_Vector *) ((const uint8_t *) src + b * row_size); + HVX_Vector * restrict v_dst = (HVX_Vector *) ((uint8_t *) dst + b * row_size); + + uint32_t boundary; + int keep_left; + switch (ttype) { + case 0: boundary = i01; keep_left = 0; break; // keep col >= row + case 1: boundary = i01 + 1; keep_left = 0; break; // keep col > row + case 2: boundary = i01 + 1; keep_left = 1; break; // keep col <= row + case 3: boundary = i01; keep_left = 1; break; // keep col < row + default: boundary = 0; keep_left = 0; break; + } + if (boundary > row_elems) boundary = row_elems; + + // Full HVX vectors — each starts at a 128-byte aligned offset + for (uint32_t i = 0; i < nvec; i++) { + const uint32_t vec_start = i * VLEN_FP32; + const uint32_t vec_end = vec_start + VLEN_FP32; + if (keep_left) { + if (vec_end <= boundary) { + v_dst[i] = v_src[i]; + } else if (vec_start >= boundary) { + v_dst[i] = zero; + } else { + HVX_VectorPred mask = Q6_Q_vsetq_R((boundary - vec_start) * sizeof(float)); + v_dst[i] = Q6_V_vmux_QVV(mask, v_src[i], zero); + } + } else { + if (vec_end <= boundary) { + v_dst[i] = zero; + } else if (vec_start >= boundary) { + v_dst[i] = v_src[i]; + } else { + HVX_VectorPred mask = Q6_Q_vsetq_R((boundary - vec_start) * sizeof(float)); + v_dst[i] = Q6_V_vmux_QVV(mask, zero, v_src[i]); + } + } + } + + // Tail elements (row_elems not a multiple of VLEN_FP32) + if (nloe > 0) { + const uint32_t vec_start = nvec * VLEN_FP32; + const uint32_t vec_end = vec_start + nloe; + HVX_Vector tail_val; + if (keep_left) { + if (vec_end <= boundary) { + tail_val = v_src[nvec]; + } else if (vec_start >= boundary) { + tail_val = zero; + } else { + HVX_VectorPred mask = Q6_Q_vsetq_R((boundary - vec_start) * sizeof(float)); + tail_val = Q6_V_vmux_QVV(mask, v_src[nvec], zero); + } + } else { + if (vec_end <= boundary) { + tail_val = zero; + } else if (vec_start >= boundary) { + tail_val = v_src[nvec]; + } else { + HVX_VectorPred mask = Q6_Q_vsetq_R((boundary - vec_start) * sizeof(float)); + tail_val = Q6_V_vmux_QVV(mask, zero, v_src[nvec]); + } + } + hvx_vec_store_a(&v_dst[nvec], nloe * sizeof(float), tail_val); + } + } +} + static void softplus_f32(const float * restrict src, float * restrict dst, uint8_t * restrict spad, @@ -498,6 +586,9 @@ static void unary_job_f32_per_thread(unsigned int nth, unsigned int ith, void * case HTP_OP_L2_NORM: l2_norm_f32(src0_spad, dst_spad, NULL, block_size, ne0, src0_row_size_aligned, op_params); break; + case HTP_OP_TRI: + tri_f32(src0_spad, dst_spad, NULL, block_size, ne00, src0_row_size_aligned, op_params, ir, uctx); + break; default: break; } @@ -571,6 +662,10 @@ static int execute_op_unary_f32(struct htp_ops_context * octx) { case HTP_OP_L2_NORM: op_type = "l2norm-f32"; break; + case HTP_OP_TRI: + op_type = "tri-f32"; + break; + default: FARF(ERROR, "Unsupported unary Op %u\n", octx->op); return HTP_STATUS_NO_SUPPORT; @@ -640,6 +735,22 @@ static int execute_op_unary_f32(struct htp_ops_context * octx) { return err; } +int op_tri(struct htp_ops_context * octx) { + int err = HTP_STATUS_OK; + + switch (octx->src[0]->type) { + case HTP_TYPE_F32: + err = execute_op_unary_f32(octx); + break; + + default: + err = HTP_STATUS_NO_SUPPORT; + break; + } + + return err; +} + int op_unary(struct htp_ops_context * octx) { int err = HTP_STATUS_OK;