Skip to content

[AMD] CI - add partitions for stage-b-test-small-1-gpu-amd #17345

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.

Sign up for GitHub

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

Merged
HaiShaw merged 2 commits into from
Jan 19, 2026
Merged

[AMD] CI - add partitions for stage-b-test-small-1-gpu-amd #17345

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
59382cf
add partitions
yctseng0211 Jan 19, 2026
f8b0100
adjust estimated time, num_threads
yctseng0211 Jan 19, 2026
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
4 changes: 2 additions & 2 deletions .github/workflows/pr-test-amd.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,7 +208,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
Expand All @@ -230,7 +230,7 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 12 --timeout-per-file 1800
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800

stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-1-amd]
Expand Down
4 changes: 2 additions & 2 deletions test/registered/amd/test_deepseek_v32_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ def setUpClass(cls):
"8",
"--enable-dp-attention",
"--model-loader-extra-config",
'{"enable_multithread_load": true, "num_threads": 64}',
'{"enable_multithread_load": true}',
]
if is_in_amd_ci():
other_args += [
Expand Down Expand Up @@ -101,7 +101,7 @@ def setUpClass(cls):
"--tp",
"8",
"--model-loader-extra-config",
'{"enable_multithread_load": true, "num_threads": 64}',
'{"enable_multithread_load": true}',
]
if is_in_amd_ci():
other_args += [
Expand Down
4 changes: 2 additions & 2 deletions test/registered/amd/test_deepseek_v32_mtp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def setUpClass(cls):
"--mem-frac",
"0.7",
"--model-loader-extra-config",
'{"enable_multithread_load": true, "num_threads": 64}',
'{"enable_multithread_load": true}',
]
if is_in_amd_ci():
other_args += [
Expand Down Expand Up @@ -137,7 +137,7 @@ def setUpClass(cls):
"--mem-frac",
"0.7",
"--model-loader-extra-config",
'{"enable_multithread_load": true, "num_threads": 64}',
'{"enable_multithread_load": true}',
]
if is_in_amd_ci():
other_args += [
Expand Down
2 changes: 1 addition & 1 deletion test/registered/attention/test_triton_sliding_window.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@

# Sliding window attention with Triton backend (Gemma-3 model)
register_cuda_ci(est_time=100, suite="stage-b-test-large-1-gpu")
register_amd_ci(est_time=100, suite="stage-b-test-small-1-gpu-amd")
register_amd_ci(est_time=200, suite="stage-b-test-small-1-gpu-amd")
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve maintainability, it's helpful to document 'magic numbers'. Please consider adding an inline comment to explain why the estimated time is being increased to 200 seconds. This will provide context for future developers who might need to adjust this value again.

Suggested change
register_amd_ci(est_time=200, suite="stage-b-test-small-1-gpu-amd")
register_amd_ci(est_time=200, suite="stage-b-test-small-1-gpu-amd") # Increased to 200s to prevent timeouts on AMD CI.



class TestSlidingWindowAttentionTriton(CustomTestCase):
Expand Down
2 changes: 1 addition & 1 deletion test/registered/openai_server/basic/test_openai_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
)

register_cuda_ci(est_time=184, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=149, suite="stage-b-test-small-1-gpu-amd")
register_amd_ci(est_time=200, suite="stage-b-test-small-1-gpu-amd")


class TestOpenAIServer(CustomTestCase):
Expand Down
Loading