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.

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

Resolve CPU llm smoke / integration test hangs by temporarily removing 8-request testcases #1028

Merged
merged 7 commits into from
Mar 6, 2025
Merged

Resolve CPU llm smoke / integration test hangs by temporarily removing 8-request testcases #1028

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
34352fb
move
renxida Mar 4, 2025
027f9f3
only smoke test up to bs4
renxida Mar 4, 2025
c860316
remove 8 concurrent requests tests from all
renxida Mar 4, 2025
f0f91bd
Merge branch 'main' into move-off-flaky-server
renxida Mar 5, 2025
7e3a50d
Merge branch 'main' into move-off-flaky-server
renxida Mar 5, 2025
033231d
use ubuntu 24.04 as runner
renxida Mar 6, 2025
7d0eddd
Merge branch 'main' into move-off-flaky-server
renxida Mar 6, 2025
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
2 changes: 1 addition & 1 deletion .github/workflows/pkgci_shark_ai.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ jobs:
matrix:
include:
- name: cpu
runs-on: azure-cpubuilder-linux-scale
runs-on: ubuntu-24.04
test_device: cpu
python-version: 3.11
- name: amdgpu_rocm_mi300_gfx942
Expand Down
8 changes: 7 additions & 1 deletion app_tests/integration_tests/llm/shortfin/meta_llama31_8b_llm_server_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,13 @@ def test_basic_generation_input_ids(
message=f"Generation did not match expected pattern.\nExpected to start with: {expected_prefix}\nActual response: {response}",
)

@pytest.mark.parametrize("concurrent_requests", [2, 4, 8])
@pytest.mark.parametrize(
"concurrent_requests",
[
2,
4,
],
)
def test_concurrent_generation(
self, server: tuple[Any, int], concurrent_requests: int
) -> None:
Expand Down
2 changes: 1 addition & 1 deletion app_tests/integration_tests/llm/shortfin/open_llama_3b_llm_server_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ def test_basic_generation_input_ids(
message=f"Generation did not match expected pattern.\nExpected to start with: {expected_prefix}\nActual response: {response}",
)

@pytest.mark.parametrize("concurrent_requests", [2, 4, 8])
@pytest.mark.parametrize("concurrent_requests", [2, 4])
def test_concurrent_generation(
self, server: tuple[Any, int], concurrent_requests: int
) -> None:
Expand Down
8 changes: 7 additions & 1 deletion app_tests/integration_tests/llm/shortfin/tinystories_llama2_25m_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,13 @@ def test_basic_generation(self, server: tuple[Any, int]) -> None:
message=f"Generation did not match expected pattern.\nExpected to start with: {expected_prefix}\nActual response: {response}",
)

@pytest.mark.parametrize("concurrent_requests", [2, 4, 8])
@pytest.mark.parametrize(
"concurrent_requests",
[
2,
4,
],
)
def test_concurrent_generation(
self, server: tuple[Any, int], concurrent_requests: int
) -> None:
Expand Down
Loading