20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[ci/build] fix gh200 test (#12681)

Browse Source 
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
youkaichao 2025-02-03 15:59:49 +08:00 committed by GitHub
parent ad4a9dc817
commit 1298a400e8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.buildkite/check-wheel-size.py
View File

@ -4,11 +4,11 @@ import os
import sys
import zipfile
# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 300 MiB
# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 400 MiB
# Note that we have 400 MiB quota, please use it wisely.
# See https://github.com/pypi/support/issues/3792 .
# Please also sync the value with the one in Dockerfile.
VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 300))
VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 400))
def print_top_10_largest_files(zip_file):

4
.buildkite/run-gh200-test.sh
View File

@ -23,6 +23,6 @@ trap remove_docker_container EXIT
remove_docker_container
# Run the image and test offline inference
docker run --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
python3 examples/offline_inference/basic.py
docker run -e HF_TOKEN -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
python3 examples/offline_inference/cli.py --model meta-llama/Llama-3.2-1B
'

2
Dockerfile
View File

@ -127,7 +127,7 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
# Check the size of the wheel if RUN_WHEEL_CHECK is true
COPY .buildkite/check-wheel-size.py check-wheel-size.py
# sync the default value with .buildkite/check-wheel-size.py
ARG VLLM_MAX_SIZE_MB=300
ARG VLLM_MAX_SIZE_MB=400
ENV VLLM_MAX_SIZE_MB=$VLLM_MAX_SIZE_MB
ARG RUN_WHEEL_CHECK=true
RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \