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>
22 lines
457 B
YAML
22 lines
457 B
YAML
group: Samplers
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Samplers Test
|
|
timeout_in_minutes: 75
|
|
source_file_dependencies:
|
|
- vllm/model_executor/layers
|
|
- vllm/sampling_metadata.py
|
|
- tests/samplers
|
|
- tests/conftest.py
|
|
commands:
|
|
- pytest -v -s samplers
|
|
- VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers
|
|
mirror:
|
|
amd:
|
|
device: mi325_1
|
|
depends_on:
|
|
- image-build-amd
|
|
commands:
|
|
- pytest -v -s samplers
|