diff --git a/.github/workflows/dynamo-pipeline.yml b/.github/workflows/dynamo-pipeline.yml index 022abb9414ef..20e364ac0501 100644 --- a/.github/workflows/dynamo-pipeline.yml +++ b/.github/workflows/dynamo-pipeline.yml @@ -25,9 +25,10 @@ on: type: boolean default: false build_timeout_minutes: + description: 'Timeout for the image build job. Matches the 60 min the other framework builds get in pr.yaml.' required: false type: number - default: 30 + default: 60 no_cache: description: 'Disable BuildKit cache-from/to. Nightly sets true for regression detection.' required: false diff --git a/container/compliance/native_packages.yaml b/container/compliance/native_packages.yaml index 5707dfd75151..7d7340e55f57 100644 --- a/container/compliance/native_packages.yaml +++ b/container/compliance/native_packages.yaml @@ -87,7 +87,7 @@ packages: # UCX — Unified Communication X, built from source in wheel_builder and used by # the NIXL transport. Installed to /usr/local (no dpkg metadata). - name: UCX - version: v1.20.x + version: v1.21.0 license: BSD-3-Clause source: https://github.com/openucx/ucx images: diff --git a/container/context.yaml b/container/context.yaml index 60569c51dd86..2e8b31b442a0 100644 --- a/container/context.yaml +++ b/container/context.yaml @@ -42,9 +42,8 @@ dynamo: etcd_version: v3.5.30 nixl_ref: v1.0.1 - nixl_ucx_ref: v1.20.x + nixl_ucx_ref: v1.21.0 nixl_gdrcopy_ref: v2.5.2 - nixl_ucx_efa_ref: 9d2b88a1f67faf9876f267658bd077b379b8bb76 nixl_libfabric_repo: https://github.com/ofiwg/libfabric.git nixl_libfabric_ref: v2.4.0 # Keep in sync with upstream NIXL's contrib/Dockerfile.manylinux. diff --git a/container/templates/wheel_builder.Dockerfile b/container/templates/wheel_builder.Dockerfile index 79e64cdbfa16..2f05d43dca2d 100644 --- a/container/templates/wheel_builder.Dockerfile +++ b/container/templates/wheel_builder.Dockerfile @@ -77,9 +77,6 @@ ADD --checksum=sha256:f60e802b6f41350393e34b24793db888a8be514054769bd17e7a6e9c0c https://github.com/intel/xpumanager/releases/download/v1.3.6/xpu-smi_1.3.6_20260206.143628.1004f6cb.u24.04_amd64.deb \ /tmp/xpu-smi.deb -# Fetch UCX patch -RUN wget --tries=3 --waitretry=5 https://raw.githubusercontent.com/intel/llm-scaler/35a14cbc08d714f460a29b7a7328df5620c8530f/vllm/patches/ai-dynamo-xpu/patches/ucx-v1.12.0.patch -O /tmp/ucx.patch - # Install xpu-smi without explicitly changing the Intel compute runtime stack. RUN apt-get update && \ apt-get install -y --no-install-recommends /tmp/xpu-smi.deb && \ @@ -376,9 +373,9 @@ RUN --mount=type=secret,id=aws-web-identity-token,target=/run/secrets/aws-token git clone https://github.com/openucx/ucx.git && \ cd ucx && \ git checkout $NIXL_UCX_REF && \ - if [ "$DEVICE" = "xpu" ]; then \ - git apply --ignore-whitespace /tmp/ucx.patch; \ - fi && \ + # The intel/llm-scaler xe-GDR patch (ucx-v1.12.0.patch) is upstream since + # UCX v1.21.0 (ib_md.c xe srcversion check, ze_copy_md.c HOST bit); restore + # the fetch + git apply for DEVICE=xpu if this ref ever drops below v1.21.0. ./autogen.sh && \ if [ "$DEVICE" = "xpu" ]; then \ ./contrib/configure-release \