Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CI/Build] AMD CI pipeline with extended set of tests. #4267

Merged
merged 37 commits into from
May 2, 2024
Merged
Changes from 1 commit
Commits
Show all changes
37 commits
Select commit Hold shift + click to select a range
5ca5b12
AMD CI pipeline with extended set of tests.
Alexei-V-Ivanov-AMD Apr 22, 2024
c43169f
Correction.
Alexei-V-Ivanov-AMD Apr 22, 2024
49206a5
Another correction.
Alexei-V-Ivanov-AMD Apr 22, 2024
9becdfb
Correction ++
Alexei-V-Ivanov-AMD Apr 22, 2024
7b53280
New build.
Alexei-V-Ivanov-AMD Apr 22, 2024
d45036b
Merge branch 'vllm-project:main' into extended_amdci
Alexei-V-Ivanov-AMD Apr 22, 2024
4f1a36b
Merge branch 'vllm-project:main' into extended_amdci
Alexei-V-Ivanov-AMD Apr 25, 2024
ac196f9
Update run-amd-test_distributed.sh
Alexei-V-Ivanov-AMD Apr 25, 2024
ff2f28f
Update Dockerfile.rocm
Alexei-V-Ivanov-AMD Apr 25, 2024
e4b52c4
Update run-amd-test_speculative_decoding.sh
Alexei-V-Ivanov-AMD Apr 25, 2024
ad960c7
Removing unnecessary replication of amd-test files.
Alexei-V-Ivanov-AMD Apr 29, 2024
0db9072
Fix.
Alexei-V-Ivanov-AMD Apr 29, 2024
bfcd53f
Removing redundant amd-test scripts.
Alexei-V-Ivanov-AMD Apr 29, 2024
f6386fa
Fixing syntax.
Alexei-V-Ivanov-AMD Apr 29, 2024
ba3b398
Adding more tests.
Alexei-V-Ivanov-AMD Apr 29, 2024
b43fbc5
Registering new tests.
Alexei-V-Ivanov-AMD Apr 29, 2024
7316136
Minor fixes.
Alexei-V-Ivanov-AMD Apr 29, 2024
2845480
Merge branch 'extended_amdci_v2' into extended_amdci
Alexei-V-Ivanov-AMD Apr 29, 2024
d60640b
use templating to reduce complexty
simon-mo Apr 30, 2024
29d836a
endif
simon-mo Apr 30, 2024
c32e5ce
fix syntax
simon-mo Apr 30, 2024
d5f0d9f
run hardware build faster
simon-mo Apr 30, 2024
df1d3d7
setup group ignore depends
simon-mo Apr 30, 2024
5f6b49a
add back container cleanup
simon-mo Apr 30, 2024
781c172
Merge branch 'vllm-project:main' into extended_amdci
Alexei-V-Ivanov-AMD May 1, 2024
295bffe
Update Dockerfile.rocm
Alexei-V-Ivanov-AMD May 1, 2024
8dbbf00
Update .buildkite/test-template.j2
Alexei-V-Ivanov-AMD May 1, 2024
e48b098
Merge branch 'vllm-project:main' into extended_amdci
Alexei-V-Ivanov-AMD May 1, 2024
420e395
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
7433522
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
bc77233
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
5f6b434
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
0d8deac
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
b2bd969
Reverting quotation back to the original state in run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
0800063
Update run-amd-test.sh
Alexei-V-Ivanov-AMD May 1, 2024
2b58db6
Merge branch 'main' into extended_amdci
Alexei-V-Ivanov-AMD May 2, 2024
7a98927
Merge branch 'vllm-project:main' into extended_amdci
Alexei-V-Ivanov-AMD May 2, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Fixing syntax.
  • Loading branch information
Alexei-V-Ivanov-AMD committed Apr 29, 2024
commit f6386fa9515ae52bb980ab808d9b589bd57145ef
56 changes: 28 additions & 28 deletions .buildkite/run-amd-test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -24,9 +24,9 @@ case ${2} in
##################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_default || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_default || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_default rocm_${1} python3 -m vllm.entrypoints.api_server &
Expand Down Expand Up @@ -70,9 +70,9 @@ case ${2} in
###############

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_core || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_test_core || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_core \
Expand All @@ -88,11 +88,11 @@ case ${2} in
######################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_distributed || true; \
remove_docker_container() { docker rm -f rocm_${1}_test_distributed || true; \
docker rm -f rocm_${1}_test_basic_distributed_correctness_opt || true; \
docker rm -f rocm_${1}_test_basic_distributed_correctness_opt || true; }
trap remove_docker_container EXIT
remove_docker_container
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
#docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_distributed \
Expand Down Expand Up @@ -121,12 +121,12 @@ case ${2} in
##################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_offline_inference || true; \
remove_docker_container() { docker rm -f rocm_${1}_test_offline_inference || true; \
docker rm -f rocm_test_${1}_offline_inference_with_prefix || true; \
docker rm -f rocm_test_${1}_llm_engine_example || true; \
docker rm -f rocm_test_${1}_llava_example || true;}
trap remove_docker_container EXIT
remove_docker_container
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host \
Expand Down Expand Up @@ -158,9 +158,9 @@ case ${2} in
#########################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_prefix_caching || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_test_prefix_caching || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_prefix_caching \
Expand All @@ -176,9 +176,9 @@ case ${2} in
##########################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_logits_processor || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_test_logits_processor || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_logits_processor \
Expand All @@ -191,9 +191,9 @@ case ${2} in
#################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_worker || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_test_worker || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_worker \
Expand All @@ -203,9 +203,9 @@ case ${2} in
# AMD Speculative Decoding Test
###############################
# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_speculative_decoding || true; }
trap remove_docker_container EXIT
remove_docker_container
remove_docker_container() { docker rm -f rocm_${1}_test_speculative_decoding || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}

# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm_${1}_test_speculative_decoding \
Expand Down Expand Up @@ -236,10 +236,10 @@ case ${2} in
#####################

# Setup cleanup
remove_docker_container(${1}) { docker rm -f rocm_${1}_test_benchmarks || true; }
trap remove_docker_container EXIT
remove_docker_container

remove_docker_container() { docker rm -f rocm_${1}_test_benchmarks || true; }
trap "remove_docker_container ${1}" EXIT
remove_docker_container ${1}
# Run the image
docker run --device /dev/kfd --device /dev/dri --network host --name rocm-${1}_test_benchmarks \
-e HF_TOKEN rocm_${1} /bin/bash -c "/bin/bash vllm/.buildkite/run-benchmarks.sh"
Expand Down