Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
73 lines
1.9 KiB
YAML
73 lines
1.9 KiB
YAML
group: Engine
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Engine
|
|
timeout_in_minutes: 15
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/engine
|
|
- tests/test_sequence
|
|
- tests/test_config
|
|
- tests/test_logger
|
|
- tests/test_vllm_port
|
|
commands:
|
|
- pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py
|
|
|
|
- label: Engine (1 GPU)
|
|
timeout_in_minutes: 30
|
|
source_file_dependencies:
|
|
- vllm/v1/engine/
|
|
- tests/v1/engine/
|
|
commands:
|
|
- pytest -v -s v1/engine/test_preprocess_error_handling.py
|
|
- pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py
|
|
|
|
- label: e2e Scheduling (1 GPU)
|
|
timeout_in_minutes: 30
|
|
source_file_dependencies:
|
|
- vllm/v1/
|
|
- tests/v1/e2e/general/
|
|
commands:
|
|
- pytest -v -s v1/e2e/general/test_async_scheduling.py
|
|
|
|
- label: e2e Core (1 GPU)
|
|
timeout_in_minutes: 30
|
|
source_file_dependencies:
|
|
- vllm/v1/
|
|
- tests/v1/e2e/general/
|
|
commands:
|
|
- pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
|
|
|
|
- label: V1 e2e (2 GPUs)
|
|
timeout_in_minutes: 60 # TODO: Fix timeout after we have more confidence in the test stability
|
|
optional: true
|
|
num_devices: 2
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/v1/e2e
|
|
commands:
|
|
# Only run tests that need exactly 2 GPUs
|
|
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "tensor_parallelism"
|
|
mirror:
|
|
amd:
|
|
device: mi325_2
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: V1 e2e (4 GPUs)
|
|
timeout_in_minutes: 60 # TODO: Fix timeout after we have more confidence in the test stability
|
|
optional: true
|
|
num_devices: 4
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/v1/e2e
|
|
commands:
|
|
# Only run tests that need 4 GPUs
|
|
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle_correctness_heavy"
|
|
mirror:
|
|
amd:
|
|
device: mi325_4
|
|
depends_on:
|
|
- image-build-amd
|