[Hardware][AMD][CI] Fix e2e core test group (#46024)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
93bad11912
commit
dced290769
@@ -647,7 +647,7 @@ steps:
|
|||||||
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
|
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
|
||||||
|
|
||||||
- label: e2e Core (1 GPU) # TBD
|
- label: e2e Core (1 GPU) # TBD
|
||||||
timeout_in_minutes: 180
|
timeout_in_minutes: 35
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
|
||||||
agent_pool: mi250_1
|
agent_pool: mi250_1
|
||||||
optional: true
|
optional: true
|
||||||
@@ -2075,19 +2075,6 @@ steps:
|
|||||||
- export VLLM_ALLOW_INSECURE_SERIALIZATION=1
|
- export VLLM_ALLOW_INSECURE_SERIALIZATION=1
|
||||||
- pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test
|
- pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test
|
||||||
|
|
||||||
- label: e2e Core (1 GPU) # TBD
|
|
||||||
timeout_in_minutes: 180
|
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
|
|
||||||
agent_pool: mi300_1
|
|
||||||
optional: true
|
|
||||||
working_dir: "/vllm-workspace/tests"
|
|
||||||
source_file_dependencies:
|
|
||||||
- vllm/v1/
|
|
||||||
- tests/v1/e2e/
|
|
||||||
- vllm/platforms/rocm.py
|
|
||||||
commands:
|
|
||||||
- pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
|
|
||||||
|
|
||||||
- label: e2e Scheduling (1 GPU) # TBD
|
- label: e2e Scheduling (1 GPU) # TBD
|
||||||
timeout_in_minutes: 180
|
timeout_in_minutes: 180
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
|
||||||
|
|||||||
@@ -74,6 +74,16 @@ steps:
|
|||||||
- tests/v1/e2e/general/
|
- tests/v1/e2e/general/
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
|
- pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
device: mi250_1
|
||||||
|
timeout_in_minutes: 35
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/v1/
|
||||||
|
- tests/v1/e2e/general/
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
|
||||||
- label: V1 e2e (2 GPUs)
|
- label: V1 e2e (2 GPUs)
|
||||||
key: v1-e2e-2-gpus
|
key: v1-e2e-2-gpus
|
||||||
|
|||||||
@@ -4,9 +4,16 @@
|
|||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
from vllm import LLM, SamplingParams
|
from vllm import LLM, SamplingParams
|
||||||
|
from vllm.platforms import current_platform
|
||||||
|
|
||||||
from ....utils import create_new_process_for_each_test
|
from ....utils import create_new_process_for_each_test
|
||||||
|
|
||||||
|
if current_platform.is_rocm():
|
||||||
|
pytest.skip(
|
||||||
|
"Cascade attention backends FLASH_ATTN and FLASHINFER are notsupported on ROCm",
|
||||||
|
allow_module_level=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
@create_new_process_for_each_test()
|
@create_new_process_for_each_test()
|
||||||
@pytest.mark.parametrize("attn_backend", ["FLASH_ATTN", "FLASHINFER"])
|
@pytest.mark.parametrize("attn_backend", ["FLASH_ATTN", "FLASHINFER"])
|
||||||
|
|||||||
Reference in New Issue
Block a user