[CI] Enable Zen CPU image build on AMD CI (#60016)
Signed-off-by: Chinmay Kulkarni <Chinmay.Kulkarni@amd.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
Chinmay-Kulkarni-AMD
co-authored by
Cursor
Micah Williamson
Cursor
Micah Williamson
parent
f0a5f111f2
commit
dd30786fef
@@ -232,3 +232,57 @@ steps:
|
||||
"$$BUILDKITE_PARALLEL_JOB"
|
||||
"$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
|
||||
parallelism: 3
|
||||
|
||||
- label: ":docker: Build Zen CPU image"
|
||||
key: zen-cpu-image-build
|
||||
# Reuse the shared `<repo>:<commit>-cpu` image that image-build-cpu publishes
|
||||
# to public ECR, so Dockerfile.zen just layers on top instead of recompiling
|
||||
# vLLM from source. If the pull fails, the build script still falls back to
|
||||
# building the CPU base from source.
|
||||
depends_on:
|
||||
- image-build-cpu
|
||||
soft_fail: true
|
||||
agents:
|
||||
queue: amd-cpu
|
||||
source_file_dependencies:
|
||||
- .buildkite/hardware_tests/cpu.yaml
|
||||
- .buildkite/image_build/image_build_zen_cpu.sh
|
||||
- docker/Dockerfile.zen
|
||||
- docker/Dockerfile.cpu
|
||||
- requirements/cpu.txt
|
||||
- requirements/build/cpu.txt
|
||||
- requirements/test/cpu.txt
|
||||
- cmake/cpu_extension.cmake
|
||||
- vllm/model_executor/layers/utils.py
|
||||
- vllm/model_executor/kernels/linear/zentorch_utils.py
|
||||
- vllm/model_executor/kernels/linear/scaled_mm/zentorch.py
|
||||
- vllm/model_executor/kernels/linear/mixed_precision/zentorch.py
|
||||
- vllm/platforms/cpu.py
|
||||
- vllm/platforms/zen_cpu.py
|
||||
- vllm/platforms/__init__.py
|
||||
- tests/model_executor/test_cpu_unquantized_gemm_dispatch.py
|
||||
- tests/test_zen_cpu_platform_detection.py
|
||||
- tests/kernels/moe/test_zen_cpu_fused_moe.py
|
||||
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
||||
- vllm/v1/attention/backends/zentorch_sdpa.py
|
||||
- tests/test_zentorch_version_pin.py
|
||||
- vllm/v1/attention/backends/mla/prefill/zen_cpu_sdpa.py
|
||||
- vllm/model_executor/layers/fused_moe/experts/zentorch_moe.py
|
||||
- tests/kernels/quantization/test_zen_da8w4.py
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_zen_cpu.sh "$REGISTRY" "$REPO" "$BUILDKITE_COMMIT"
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
# Install zentorch directly (if-branch in Dockerfile.zen) instead of
|
||||
# `uv pip install "vllm[zen]"`, which forces uv to re-resolve vLLM's full
|
||||
# dependency closure and chokes on its transitive triton-cpu URL dependency.
|
||||
# Keep this pin in sync with the `zen` extra in setup.py.
|
||||
ZENTORCH_VERSION: "2.13.0.1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: 1 # Transient Docker/BuildKit failure
|
||||
limit: 1
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
+75
@@ -0,0 +1,75 @@
|
||||
#!/bin/bash
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
#
|
||||
# Build the AMD Zen CPU image (vLLM + zentorch) by layering docker/Dockerfile.zen
|
||||
# on top of a CPU base image that already has vLLM installed.
|
||||
#
|
||||
# To avoid recompiling vLLM from source, prefer reusing the shared CPU image that
|
||||
# the image-build-cpu step already builds and publishes for this commit
|
||||
# (`<repo>:<commit>-cpu`). It lives in public ECR, which allows anonymous pulls,
|
||||
# so no registry credentials are required. If the pull fails (e.g. the image
|
||||
# isn't published yet), fall back to building the base from docker/Dockerfile.cpu.
|
||||
#
|
||||
# The zen image is not pushed to a registry.
|
||||
#
|
||||
# See docker/Dockerfile.zen for the build workflow this mirrors.
|
||||
set -euo pipefail
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
|
||||
image_repo() {
|
||||
if [[ -n "${REGISTRY}" ]]; then
|
||||
printf '%s/%s' "${REGISTRY}" "${REPO}"
|
||||
else
|
||||
printf '%s' "${REPO}"
|
||||
fi
|
||||
}
|
||||
|
||||
IMAGE_REPO="$(image_repo)"
|
||||
|
||||
# The shared CPU image published by image-build-cpu (public ECR, anonymous pull).
|
||||
SHARED_CPU_IMAGE=""
|
||||
if [[ -n "${REGISTRY}" ]]; then
|
||||
SHARED_CPU_IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-cpu"
|
||||
fi
|
||||
FALLBACK_BASE_IMAGE="zen-cpu-base:$BUILDKITE_COMMIT"
|
||||
IMAGE="$IMAGE_REPO:$BUILDKITE_COMMIT-zen-cpu"
|
||||
|
||||
# ZENTORCH_VERSION is optional; when unset the Dockerfile falls back to
|
||||
# installing zentorch via `vllm[zen]`.
|
||||
ZENTORCH_VERSION=${ZENTORCH_VERSION:-}
|
||||
|
||||
# Step 1: obtain the CPU base image that Dockerfile.zen layers on. Prefer pulling
|
||||
# the published `-cpu` image; fall back to building it from source if unavailable.
|
||||
if [[ -n "${SHARED_CPU_IMAGE}" ]] && docker pull "$SHARED_CPU_IMAGE"; then
|
||||
echo "--- :docker: Using published CPU image as base: $SHARED_CPU_IMAGE"
|
||||
BASE_IMAGE="$SHARED_CPU_IMAGE"
|
||||
else
|
||||
echo "--- :docker: Published CPU image unavailable; building base from source"
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--platform linux/amd64 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--build-arg VLLM_CPU_X86=true \
|
||||
--tag "$FALLBACK_BASE_IMAGE" \
|
||||
--target vllm-openai \
|
||||
--progress plain .
|
||||
BASE_IMAGE="$FALLBACK_BASE_IMAGE"
|
||||
fi
|
||||
|
||||
# Step 2: build the zen test image on top of the CPU base.
|
||||
echo "--- :docker: Building Zen test image"
|
||||
docker build --file docker/Dockerfile.zen \
|
||||
--platform linux/amd64 \
|
||||
--build-arg BASE_IMAGE="$BASE_IMAGE" \
|
||||
${ZENTORCH_VERSION:+--build-arg ZENTORCH_VERSION="$ZENTORCH_VERSION"} \
|
||||
--tag "$IMAGE" \
|
||||
--target vllm-zen-test \
|
||||
--progress plain .
|
||||
Reference in New Issue
Block a user