[CI] Run GH200 test on the shared arm64 CI image (#60253)
Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
Kevin H. Luu
parent
8d10c38b73
commit
ab905a885d
@@ -2,10 +2,15 @@ group: Hardware
|
||||
steps:
|
||||
- label: "GH200 Test"
|
||||
key: gh200-test
|
||||
timeout_in_minutes: 30
|
||||
soft_fail: true
|
||||
device: gh200
|
||||
no_plugin: true
|
||||
optional: true
|
||||
commands:
|
||||
- nvidia-smi
|
||||
- bash .buildkite/scripts/hardware_ci/run-gh200-test.sh
|
||||
working_dir: "/vllm-workspace"
|
||||
depends_on:
|
||||
- arm64-image-build
|
||||
env:
|
||||
VLLM_WORKER_MULTIPROC_METHOD: "spawn"
|
||||
commands:
|
||||
- nvidia-smi
|
||||
- python3 examples/basic/offline_inference/generate.py --model meta-llama/Llama-3.2-1B
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
# This script build the GH200 docker image and run the offline inference inside the container.
|
||||
# It serves a sanity check for compilation and basic model usage.
|
||||
set -ex
|
||||
|
||||
# Skip the new torch installation during build since we are using the specified version for arm64 in the Dockerfile
|
||||
python3 tools/use_existing_torch.py
|
||||
|
||||
# Try building the docker image
|
||||
DOCKER_BUILDKIT=1 docker build . \
|
||||
--file docker/Dockerfile \
|
||||
--target vllm-openai \
|
||||
--platform "linux/arm64" \
|
||||
-t gh200-test \
|
||||
--build-arg max_jobs=66 \
|
||||
--build-arg nvcc_threads=2 \
|
||||
--build-arg BUILD_BASE_IMAGE=pytorch/manylinuxaarch64-builder:cuda13.0-b8b5f17a7d9ccfc25bbc5cf17b3fcea12964a042 \
|
||||
--build-arg torch_cuda_arch_list="9.0+PTX"
|
||||
|
||||
# Setup cleanup
|
||||
remove_docker_container() { docker rm -f gh200-test || true; }
|
||||
trap remove_docker_container EXIT
|
||||
remove_docker_container
|
||||
|
||||
# Run the image and test offline inference
|
||||
docker run -e HF_TOKEN -e VLLM_WORKER_MULTIPROC_METHOD=spawn -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
|
||||
python3 examples/basic/offline_inference/generate.py --model meta-llama/Llama-3.2-1B
|
||||
'
|
||||
Reference in New Issue
Block a user